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

    Neuronpedia

    INDEX
    Explanations

    database, location, scope, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝓶
    1.04
     esimerk
    1.03
    アイデア
    1.01
    まったく
    0.99
    abilă
    0.96
    ég
    0.95
    İŞ
    0.94
     기다
    0.94
     எடுத்துக்கா
    0.94
    സ്
    0.93
    POSITIVE LOGITS
     consecrated
    0.93
    า
    0.91
    ClNO
    0.90
     aparato
    0.89
    ಿವೆ
    0.88
     Jum
    0.87
    nsics
    0.86
     Hause
    0.86
    ಿತ್ತು
    0.85
    很多的
    0.85
    Act Density 0.000%

    No Known Activations