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

    Neuronpedia

    INDEX
    Explanations

    management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bershka
    -0.63
     réguli
    -0.62
     démocr
    -0.60
     rêver
    -0.60
     magnétique
    -0.59
     pitié
    -0.59
     pleaſure
    -0.59
    ыгана
    -0.59
     estudian
    -0.59
     binocular
    -0.58
    POSITIVE LOGITS
    WebElementEntity
    0.63
    parseFrom
    0.50
    niająca
    0.47
    ftagPool
    0.46
    StoreMessageInfo
    0.44
    kha
    0.43
    制
    0.43
     kasarigan
    0.42
     system
    0.42
    Autoritní
    0.40
    Act Density 0.007%

    No Known Activations