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

    Neuronpedia

    INDEX
    Explanations

    bind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deform
    -0.07
    \">↵
    -0.07
     sperma
    -0.07
     输出
    -0.07
    wh
    -0.06
    _packet
    -0.06
    +'&
    -0.06
     paso
    -0.06
     >(
    -0.06
    Packages
    -0.06
    POSITIVE LOGITS
     coeff
    0.07
    encoding
    0.06
     AVL
    0.06
    patients
    0.06
     quart
    0.06
    reich
    0.06
    pygame
    0.06
    عال
    0.06
     jointly
    0.06
    �
    0.06
    Act Density 0.004%

    No Known Activations