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

    Neuronpedia

    INDEX
    Explanations

    trading strategies and code conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    媝
    0.46
     vecteur
    0.44
     Womens
    0.43
    ጶ
    0.42
     participle
    0.42
    比如說
    0.41
     भूगोल
    0.40
     жінок
    0.40
    दारी
    0.40
    товано
    0.40
    POSITIVE LOGITS
     and
    0.48
    a
    0.42
    t
    0.42
     de
    0.40
     Benz
    0.40
     Ch
    0.40
    s
    0.40
     Ts
    0.39
    S
    0.39
     metal
    0.39
    Act Density 0.000%

    No Known Activations