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

    Neuronpedia

    INDEX
    Explanations

    function calls and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Trie
    0.85
     "/
    0.84
     [];
    0.84
     Horizonte
    0.81
     isValid
    0.80
     '/
    0.80
     />';
    0.78
     "[
    0.77
    リーブ
    0.77
     调用
    0.75
    POSITIVE LOGITS
    (
    0.80
    ation
    0.74
     of
    0.71
    used
    0.70
    casts
    0.69
    gest
    0.68
    casting
    0.67
    cast
    0.67
    lest
    0.67
    ales
    0.66
    Act Density 0.180%

    No Known Activations