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

    Neuronpedia

    INDEX
    Explanations

    Book formatting notations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     thuế
    -0.07
    toDouble
    -0.07
    酡
    -0.07
    听见
    -0.07
     laugh
    -0.07
    stdarg
    -0.06
     siècle
    -0.06
     الصحفي
    -0.06
    谿
    -0.06
    POSITIVE LOGITS
    _regions
    0.07
     undercover
    0.07
    TARGET
    0.06
    ctal
    0.06
     Outs
    0.06
     khủng
    0.06
    OURCE
    0.06
    インター�
    0.06
    ольз
    0.06
     Lip
    0.06
    Act Density 0.005%

    No Known Activations