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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hash
    -0.07
    addListener
    -0.06
     dias
    -0.06
     опред
    -0.06
    Snake
    -0.06
    compan
    -0.06
    ќ
    -0.06
    _initializer
    -0.06
    гал
    -0.06
    в
    -0.06
    POSITIVE LOGITS
     Emb
    0.06
    依
    0.06
     protests
    0.06
    eking
    0.06
     Finals
    0.06
     Tweet
    0.06
    484
    0.06
     Eis
    0.06
     yiy
    0.06
    _cover
    0.06
    Act Density 0.000%

    No Known Activations