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

    Neuronpedia

    INDEX
    Explanations

    tens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♀♀♀♀
    -0.07
     невозможно
    -0.07
    ovenant
    -0.06
    lament
    -0.06
    .dataTables
    -0.06
    _intro
    -0.06
    .users
    -0.06
    erging
    -0.06
    ocyte
    -0.06
    roduction
    -0.06
    POSITIVE LOGITS
     tes
    0.06
    ulması
    0.06
    ZE
    0.06
    (Op
    0.06
     doz
    0.06
     turtles
    0.06
    _Check
    0.06
    Chess
    0.06
     powerful
    0.06
    _dims
    0.06
    Act Density 0.002%

    No Known Activations