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

    Neuronpedia

    INDEX
    Explanations

    names and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     homosexuality
    0.55
    ឡិចត្រូ
    0.54
    PlayerDataCache
    0.54
    getTargetContext
    0.53
    𒁾
    0.53
    レザー
    0.52
    odiazep
    0.51
     Temperatura
    0.51
     앉
    0.50
     배경
    0.50
    POSITIVE LOGITS
    (
    0.64
    '
    0.62
    s
    0.61
    по
    0.59
    amos
    0.57
    I
    0.57
    اري
    0.55
    Av
    0.55
    নি
    0.54
    ücklich
    0.54
    Act Density 0.000%

    No Known Activations