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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

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

    Mathematical or symbolic notation

    np_acts-logits-general · gemini-2.0-flash

    special characters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tró
    -0.60
    tagHelperRunner
    -0.56
    entras
    -0.55
     CreateTagHelper
    -0.51
    zuf
    -0.50
    graves
    -0.50
    atorship
    -0.50
     pozost
    -0.48
    idge
    -0.47
     Wie
    -0.46
    POSITIVE LOGITS
    expandindo
    0.69
    Cyfeiriadau
    0.64
     nebu
    0.61
     kaarangay
    0.61
    consulté
    0.58
    ConstraintMaker
    0.58
    TagMode
    0.56
    InjectAttribute
    0.54
     виправивши
    0.52
    taminophen
    0.51
    Act Density 0.074%

    No Known Activations