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

    Neuronpedia

    INDEX
    Explanations

    By

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     murderers
    -0.07
     nej
    -0.07
     tease
    -0.07
     Canton
    -0.07
     Goes
    -0.07
    DBus
    -0.07
     Nej
    -0.07
     Pyongyang
    -0.06
     feelings
    -0.06
    -campus
    -0.06
    POSITIVE LOGITS
     žen
    0.07
     shore
    0.06
    ncy
    0.06
     huz
    0.06
    <_
    0.06
     Exped
    0.06
    uft
    0.06
    onnement
    0.06
    .metrics
    0.06
     adequately
    0.06
    Act Density 0.001%

    No Known Activations