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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horses
    -0.06
     pc
    -0.06
    )|
    -0.06
    {x
    -0.06
    )x
    -0.06
    shopping
    -0.06
     geographic
    -0.06
    akh
    -0.06
    اتر
    -0.06
    Enemies
    -0.06
    POSITIVE LOGITS
     Cool
    0.07
    ılıç
    0.06
    _PRED
    0.06
    wg
    0.06
     sola
    0.06
    extend
    0.06
    _buffer
    0.06
    <=$
    0.06
    affiliate
    0.06
     uid
    0.06
    Act Density 0.044%

    No Known Activations