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

    Neuronpedia

    INDEX
    Explanations

    business outlooks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشين
    -1.02
     judgment
    -0.92
     judgement
    -0.91
    judgment
    -0.90
    NUMX
    -0.89
     judgements
    -0.84
     Judgement
    -0.80
    ThroughAttribute
    -0.78
     judgments
    -0.75
     مرئيه
    -0.74
    POSITIVE LOGITS
    ,
    0.58
    ory
    0.57
     and
    0.53
    igslist
    0.50
    ی
    0.50
     of
    0.49
    a
    0.48
    .
    0.45
     by
    0.45
    kuva
    0.43
    Act Density 0.201%

    No Known Activations