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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dar
    -0.07
    plings
    -0.07
    Dar
    -0.07
    thead
    -0.07
     ох
    -0.06
     trot
    -0.06
    )**
    -0.06
    tyard
    -0.06
    EVER
    -0.06
    ouples
    -0.06
    POSITIVE LOGITS
    /es
    0.06
    _DEV
    0.06
     μεγ
    0.06
     objc
    0.06
     ça
    0.06
    839
    0.06
     při
    0.06
    <Box
    0.06
    .imread
    0.06
     Victory
    0.06
    Act Density 0.005%

    No Known Activations