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

    Neuronpedia

    INDEX
    Explanations

    paid time off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tenant
    0.46
     snatched
    0.46
     noticia
    0.43
     The
    0.43
     Survey
    0.43
    enton
    0.42
    featuring
    0.42
     situazione
    0.42
    ς
    0.42
     pants
    0.42
    POSITIVE LOGITS
     colds
    0.58
    是因为
    0.54
    aile
    0.54
    マ
    0.53
    ποιή
    0.52
     cools
    0.52
     sighs
    0.51
     sağlı
    0.50
    เป็นการ
    0.50
    وغ
    0.50
    Act Density 0.000%

    No Known Activations