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

    Neuronpedia

    INDEX
    Explanations

    internet and web access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COMPOUNDS
    0.35
     அடிக்க
    0.34
    ording
    0.34
     дохода
    0.33
     espe
    0.33
     വേദ
    0.33
    常常
    0.33
     праз
    0.32
    쑥
    0.32
    ird
    0.32
    POSITIVE LOGITS
    osphere
    0.45
    othelium
    0.39
    }^{*}$
    0.37
     chromosphere
    0.36
    ्यक्रम
    0.36
    onavírus
    0.35
    idão
    0.34
    сторінку
    0.34
    liest
    0.33
    ियम
    0.33
    Act Density 0.024%

    No Known Activations