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
    .mit
    -0.07
     어느
    -0.07
    _publish
    -0.07
    ğe
    -0.06
    reg
    -0.06
    äs
    -0.06
    かい
    -0.06
    JM
    -0.06
    _DECLARE
    -0.06
    761
    -0.06
    POSITIVE LOGITS
    Fed
    0.07
    拼
    0.06
     erotica
    0.06
    =-=-
    0.06
     rib
    0.06
     Kok
    0.06
     축
    0.06
    $email
    0.06
     ー
    0.06
    complex
    0.06
    Act Density 0.051%

    No Known Activations