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

    Neuronpedia

    INDEX
    Explanations

    import statements * import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வராக
    0.43
    ovalo
    0.41
     numberOfRows
    0.41
    ğine
    0.39
     ஓவிய
    0.39
    jTextField
    0.38
     સમાચાર
    0.37
    दारी
    0.37
    釭
    0.37
     होगी
    0.36
    POSITIVE LOGITS
     dist
    0.80
    dist
    0.74
     Dist
    0.68
    Dist
    0.63
    cjs
    0.59
    esm
    0.57
    lib
    0.56
    src
    0.55
     lib
    0.55
     src
    0.52
    Act Density 0.003%

    No Known Activations