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

    Neuronpedia

    INDEX
    Explanations

    , separating list items or variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.85
    0.77
    :
    0.76
    over
    0.72
    ной
    0.72
    í
    0.70
    ー
    0.70
    で
    0.70
        
    0.69
    이나
    0.68
    POSITIVE LOGITS
     BOARDSIZE
    0.79
     sparsim
    0.78
     aient
    0.74
     elenco
    0.73
     bawang
    0.72
    𝘥
    0.71
    msgs
    0.69
     dilwale
    0.69
    jdbcType
    0.68
     acciaio
    0.68
    Act Density 0.106%

    No Known Activations