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

    Neuronpedia

    INDEX
    Explanations

    code/file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shades
    -0.06
    aternity
    -0.06
    になる
    -0.06
     Wick
    -0.06
    ournée
    -0.06
    本当
    -0.06
     ви
    -0.06
    urdu
    -0.06
     Sus
    -0.06
     Emergency
    -0.06
    POSITIVE LOGITS
    θο
    0.07
    izyon
    0.07
    _FREQUENCY
    0.06
     ona
    0.06
    Globals
    0.06
    yah
    0.06
    .workspace
    0.06
    kap
    0.06
    ("/",
    0.06
    .isVisible
    0.06
    Act Density 0.000%

    No Known Activations