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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PIX
    -0.08
     everlasting
    -0.06
    рогра
    -0.06
    -0.06
    _pagination
    -0.06
    ूष
    -0.06
     humanoid
    -0.06
     Vlad
    -0.06
     rezerv
    -0.06
    чу
    -0.06
    POSITIVE LOGITS
    $.
    0.08
     Controller
    0.07
    igue
    0.07
     rumors
    0.07
     singular
    0.06
     موفق
    0.06
    development
    0.06
    iard
    0.06
     tiers
    0.06
    -Core
    0.06
    Act Density 0.000%

    No Known Activations