Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical inequalities and relationships among variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or programming inequality expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical inequality or assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    strerror
    -0.55
    __":
    -0.52
     Grand
    -0.48
     course
    -0.47
    siez
    -0.47
    ContentAlignment
    -0.47
    fillable
    -0.46
    AnchorStyles
    -0.46
    Decided
    -0.46
     CreateTagHelper
    -0.45
    POSITIVE LOGITS
     CURIAM
    0.66
    TagHelper
    0.63
     "..\..\
    0.63
     "..\..\..\
    0.62
    ArrowToggle
    0.61
     unknownFields
    0.58
    zzlies
    0.57
    ranton
    0.55
     resourceCulture
    0.54
     Ripper
    0.53
    Act Density 0.638%

    No Known Activations