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

    Neuronpedia

    INDEX
    Explanations

    outputs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cincinnati
    -0.07
    Uno
    -0.06
    реди
    -0.06
    ервые
    -0.06
    _server
    -0.06
    матрива
    -0.06
     magnet
    -0.06
    asca
    -0.06
    jn
    -0.06
     CAL
    -0.06
    POSITIVE LOGITS
    (wx
    0.07
    .GetUser
    0.06
    izzie
    0.06
    _COMPARE
    0.06
    (cs
    0.06
     staffing
    0.06
    (ft
    0.06
     smallest
    0.06
    .Protocol
    0.06
     fitted
    0.06
    Act Density 0.004%

    No Known Activations