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

    Neuronpedia

    INDEX
    Explanations

    sold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    となり
    -0.07
     meant
    -0.07
    "C
    -0.07
    angan
    -0.07
     يح
    -0.06
     же
    -0.06
    ื่
    -0.06
    �
    -0.06
    "The
    -0.06
    들이
    -0.06
    POSITIVE LOGITS
     castle
    0.07
     plays
    0.07
    858
    0.06
     spp
    0.06
    _instances
    0.06
    -functions
    0.06
    .mouse
    0.06
    $/)
    0.06
    .backward
    0.06
    disabled
    0.06
    Act Density 0.000%

    No Known Activations