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
     Baldwin
    -0.07
     أبو
    -0.07
     jente
    -0.06
    430
    -0.06
    250
    -0.06
     attacking
    -0.06
     thôn
    -0.06
     کامپی
    -0.06
     eaten
    -0.06
     hlav
    -0.06
    POSITIVE LOGITS
     https
    0.09
    https
    0.09
    ners
    0.07
    �
    0.07
    _processing
    0.07
    ://
    0.07
     biology
    0.07
    าศ
    0.07
     By
    0.06
    _loss
    0.06
    Act Density 0.032%

    No Known Activations