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

    Neuronpedia

    INDEX
    Explanations

    instances of ongoing or past situations that indicate problems or changes

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

    if problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.42
    coque
    -0.41
    참고
    -0.40
     withal
    -0.40
    järvi
    -0.40
     Desk
    -0.39
     Permalink
    -0.39
    desk
    -0.39
     Forder
    -0.39
     butterknife
    -0.38
    POSITIVE LOGITS
    怎麼辦
    0.66
    怎么办
    0.56
    Personendaten
    0.55
     например
    0.51
     يتيمه
    0.51
    MigrationBuilder
    0.50
    causing
    0.50
     například
    0.50
    лтемелер
    0.49
     inmediatamente
    0.48
    Act Density 0.072%

    No Known Activations