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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unters
    -0.08
    .HTML
    -0.07
     Unauthorized
    -0.07
    暂
    -0.07
     logo
    -0.07
     meat
    -0.07
    烈
    -0.06
    duto
    -0.06
     يون
    -0.06
    _TE
    -0.06
    POSITIVE LOGITS
     Auch
    0.08
     yer
    0.08
    سين
    0.07
    refixer
    0.07
    promotion
    0.07
     nuru
    0.07
    ировка
    0.06
    Rand
    0.06
    0.06
    sending
    0.06
    Act Density 0.001%

    No Known Activations