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

    Neuronpedia

    INDEX
    Explanations

    factor of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ़ी
    -0.06
    opcion
    -0.06
    (V
    -0.06
    _mc
    -0.06
    zt
    -0.06
    […]
    -0.06
    _lower
    -0.06
    textfield
    -0.06
     majors
    -0.06
     trajectories
    -0.06
    POSITIVE LOGITS
    Cod
    0.07
     Canter
    0.06
     Sk
    0.06
    ,False
    0.06
     Brit
    0.06
    comings
    0.06
     tomatoes
    0.06
    _LIBRARY
    0.06
    Fran
    0.06
     ********
    0.06
    Act Density 0.008%

    No Known Activations