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

    Neuronpedia

    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    recover
    -0.08
    -zero
    -0.07
    Intensity
    -0.06
    کات
    -0.06
    .usuario
    -0.06
     rang
    -0.06
     бу
    -0.06
    Dyn
    -0.06
    コン
    -0.06
    _cutoff
    -0.06
    POSITIVE LOGITS
    FOR
    0.07
     Psi
    0.07
     urllib
    0.07
    Such
    0.07
    See
    0.06
     wishing
    0.06
     empowered
    0.06
     dieta
    0.06
    _private
    0.06
    URNS
    0.06
    Act Density 0.006%

    No Known Activations