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

    Neuronpedia

    INDEX
    Explanations

    preferred

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    本当に
    -0.07
     situ
    -0.06
    पत
    -0.06
    raising
    -0.06
     riot
    -0.06
     Antony
    -0.06
    内の
    -0.06
     розум
    -0.06
    _lot
    -0.06
    .SetInt
    -0.06
    POSITIVE LOGITS
     preferred
    0.13
    preferred
    0.09
     Preferred
    0.09
    Preferred
    0.09
     favoured
    0.08
     favored
    0.08
     hesitate
    0.08
     chosen
    0.07
    favorite
    0.07
    Wind
    0.07
    Act Density 0.009%

    No Known Activations