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

    Neuronpedia

    INDEX
    Explanations

    say ()

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _box
    -0.08
    _ar
    -0.07
    _ci
    -0.07
     Res
    -0.07
     Epic
    -0.07
     Austin
    -0.07
     Π
    -0.06
     folders
    -0.06
    194
    -0.06
     умер
    -0.06
    POSITIVE LOGITS
     practition
    0.07
    úsqueda
    0.06
    ezpe
    0.06
    decess
    0.06
     unwitting
    0.06
     lớ
    0.06
    ("//*[@
    0.06
    insurance
    0.06
    BagConstraints
    0.06
    .UseFont
    0.06
    Act Density 0.015%

    No Known Activations