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

    Neuronpedia

    INDEX
    Explanations

    database collation settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.70
    ian
    0.66
     an
    0.61
    iness
    0.59
     .
    0.58
    ils
    0.57
     He
    0.56
    Pars
    0.56
     ii
    0.55
     beating
    0.55
    POSITIVE LOGITS
    то
    0.84
    Վ
    0.84
    ти
    0.84
    Т
    0.82
    市
    0.79
    Д
    0.78
    Ј
    0.78
    지역
    0.76
    ция
    0.75
    மாக
    0.75
    Act Density 0.001%

    No Known Activations