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

    Neuronpedia

    INDEX
    Explanations

    Phys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aurants
    -0.07
    ullo
    -0.07
    _CHO
    -0.06
     لل
    -0.06
    /pg
    -0.06
     بخش
    -0.06
    olesale
    -0.06
     revis
    -0.06
    -lock
    -0.06
    ening
    -0.06
    POSITIVE LOGITS
     #'
    0.07
    _opts
    0.07
     дорож
    0.07
    .MouseDown
    0.07
     Acts
    0.07
    事件
    0.07
     použít
    0.06
     případech
    0.06
     /////
    0.06
     closures
    0.06
    Act Density 0.119%

    No Known Activations