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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _yes
    -0.07
    /legal
    -0.07
    	offset
    -0.07
     Incredible
    -0.07
     subdivision
    -0.07
    /end
    -0.07
    ;/
    -0.07
     the
    -0.06
     of
    -0.06
    有点
    -0.06
    POSITIVE LOGITS
     Volk
    0.06
    서관
    0.06
    618
    0.06
     Alta
    0.06
     OnCollision
    0.06
    _pd
    0.06
     常
    0.06
     масла
    0.05
    656
    0.05
     را
    0.05
    Act Density 0.418%

    No Known Activations