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

    Neuronpedia

    INDEX
    Explanations

    a reminder, not nihilism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.36
     of
    0.32
    /
    0.31
    $:
    0.31
    ;
    0.31
    (
    0.30
    ...
    0.30
    #
    0.30
     juta
    0.29
    ,
    0.29
    POSITIVE LOGITS
    滢
    0.36
     नाउ
    0.33
     مسئلہ
    0.32
     मलाइका
    0.32
    ೆಯೇ
    0.32
     سنی
    0.32
     carcinogenesis
    0.31
    یعنی
    0.31
    እ
    0.31
    叁章
    0.30
    Act Density 0.001%

    No Known Activations