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

    Neuronpedia

    INDEX
    Explanations

    xml schema and namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሪ
    0.38
    沂
    0.37
    फार
    0.36
     колон
    0.35
    เนิน
    0.35
     aanwezig
    0.35
     कॉलम
    0.35
     フォー
    0.34
     уви
    0.34
    සුව
    0.34
    POSITIVE LOGITS
    XMLSchema
    0.57
    a
    0.40
    he
    0.40
    anda
    0.40
     bened
    0.39
     SM
    0.39
     definitions
    0.39
     exponents
    0.38
    lend
    0.38
    ace
    0.38
    Act Density 0.000%

    No Known Activations