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

    Neuronpedia

    INDEX
    Explanations

    "I know I do"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domains
    -0.07
    ー�
    -0.07
    prec
    -0.07
    doors
    -0.07
    Upper
    -0.06
     Anything
    -0.06
     Hunting
    -0.06
    avig
    -0.06
    JK
    -0.06
    Depth
    -0.06
    POSITIVE LOGITS
    bron
    0.07
     SqlConnection
    0.07
     décou
    0.06
     bakeca
    0.06
     analsex
    0.06
    Vectorizer
    0.06
    Env
    0.06
     Paul
    0.06
     عاش
    0.06
    'icon
    0.06
    Act Density 0.160%

    No Known Activations