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

    Neuronpedia

    INDEX
    Explanations

    personality flaws

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μο
    -0.07
    ym
    -0.07
    zier
    -0.07
    Roz
    -0.06
    े
    -0.06
     uniq
    -0.06
     ner
    -0.06
    ла
    -0.06
     we
    -0.06
     Joy
    -0.06
    POSITIVE LOGITS
    ARS
    0.07
     destined
    0.07
    TextChanged
    0.07
    taient
    0.07
    Da
    0.07
     cung
    0.06
     Trilogy
    0.06
    ANGER
    0.06
    _INVALID
    0.06
    원의
    0.06
    Act Density 0.028%

    No Known Activations