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

    Neuronpedia

    INDEX
    Explanations

    statements expressing desire or necessity regarding actions and requirements

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

    if you must or want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     couverte
    -0.35
     ajedrez
    -0.34
     myö
    -0.34
     réguli
    -0.32
    ailleurs
    -0.31
     fortæ
    -0.31
    دانشنامهٔ
    -0.31
     TextAppearance
    -0.31
     ascenso
    -0.31
    ביוגרפיה
    -0.31
    POSITIVE LOGITS
    oredCriteria
    0.52
    AppMethodBeat
    0.50
    AutoScaleMode
    0.48
     nonUne
    0.47
     autorytatywna
    0.47
    contentLoaded
    0.47
     Autorisations
    0.46
    rungsseite
    0.46
    WithIOException
    0.46
    ⏜
    0.44
    Act Density 0.043%

    No Known Activations