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

    Neuronpedia

    INDEX
    Explanations

    creating Go Playing Programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    छि
    0.48
    PropertyParam
    0.46
    劻
    0.46
    ography
    0.46
    tiden
    0.45
     Viejo
    0.45
     INVENTION
    0.44
     Buenas
    0.44
    oczy
    0.43
    전히
    0.43
    POSITIVE LOGITS
     tau
    0.44
     array
    0.44
     fast
    0.43
    lices
    0.43
    ik
    0.42
     I
    0.42
    "$
    0.41
    '
    0.41
    minimum
    0.41
    df
    0.40
    Act Density 0.001%

    No Known Activations