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

    Neuronpedia

    INDEX
    Explanations

    specific nouns with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डाउट
    0.35
    敵人
    0.33
     njima
    0.33
    的力量
    0.32
    ઠ
    0.32
    डी
    0.31
     nettoyer
    0.31
     केलेल्या
    0.31
     guarantor
    0.31
    爯
    0.31
    POSITIVE LOGITS
    ,
    0.43
     (
    0.40
     pioneered
    0.39
    ™,
    0.39
    .
    0.38
     ,
    0.38
     I
    0.36
     /
    0.36
    ],
    0.35
    /
    0.35
    Act Density 0.322%

    No Known Activations