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

    Neuronpedia

    INDEX
    Explanations

    because after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ^{
    1.27
    ിവ
    1.23
    А
    1.18
     jeopard
    1.16
     사항
    1.16
    زار
    1.16
     đam
    1.16
    naires
    1.15
     Instructions
    1.13
     laun
    1.12
    POSITIVE LOGITS
    ulfonic
    1.06
    HexString
    1.04
    Likewise
    1.01
     SSm
    0.98
    dateFormat
    0.97
    uros
    0.97
     countrymen
    0.96
    ploader
    0.96
    ১৪
    0.96
     Oreo
    0.94
    Act Density 0.001%

    No Known Activations