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

    Neuronpedia

    INDEX
    Explanations

    concepts related to significant events or observations in studies and arguments

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

    Followed by "is" or "was"

    np_acts-logits-general · gemini-2.0-flash

    statements about things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shira
    -0.49
    ².
    -0.49
    obis
    -0.47
     Karol
    -0.45
    dersfield
    -0.45
    utel
    -0.44
    FUL
    -0.43
    AddTagHelper
    -0.43
     Starship
    -0.43
    ikala
    -0.43
    POSITIVE LOGITS
     заключается
    0.53
    ViewImports
    0.43
    UserScript
    0.42
    findpost
    0.42
     HasFactory
    0.41
     lies
    0.41
    ConstraintMaker
    0.41
    蚪
    0.41
    providedIn
    0.41
     intptr
    0.39
    Act Density 0.352%

    No Known Activations