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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Template
    -0.07
    MENT
    -0.07
     Clarence
    -0.06
    Notifier
    -0.06
    An
    -0.06
    amb
    -0.06
    もり
    -0.06
     Поп
    -0.06
    znám
    -0.06
    erokee
    -0.06
    POSITIVE LOGITS
    .reason
    0.07
     counterpart
    0.06
     sophistic
    0.06
     مقایسه
    0.06
    assin
    0.06
     业
    0.06
     ij
    0.06
    ian
    0.06
    调
    0.06
    .relu
    0.06
    Act Density 0.416%

    No Known Activations