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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CWE
    -0.07
     chairs
    -0.07
    ead
    -0.07
    @c
    -0.07
    .tx
    -0.07
     lids
    -0.07
     flushed
    -0.07
    惠
    -0.07
     fp
    -0.06
    후
    -0.06
    POSITIVE LOGITS
    Difficulty
    0.08
     참여
    0.07
     باشد
    0.06
     дина
    0.06
    (prediction
    0.06
    centage
    0.06
    ंजन
    0.06
     belang
    0.06
     Duel
    0.06
    205
    0.06
    Act Density 0.000%

    No Known Activations