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

    Neuronpedia

    INDEX
    Explanations

    PHP namespaces and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    તમ
    0.64
     tetragonal
    0.61
    ပါ။
    0.59
    。
    0.56
     an
    0.56
     espa
    0.56
    odynam
    0.56
    朳
    0.55
    䩕
    0.55
    配备
    0.54
    POSITIVE LOGITS
    č
    0.55
     jadi
    0.52
    data
    0.51
    $
    0.50
     पाह
    0.48
    konen
    0.47
     décadas
    0.47
     Č
    0.46
     C
    0.46
    izioni
    0.46
    Act Density 0.008%

    No Known Activations