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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########################################################################
    -0.07
    {}'.
    -0.07
    peace
    -0.06
    〈
    -0.06
    (de
    -0.06
     باغ
    -0.06
    MeshPro
    -0.06
    ئ
    -0.06
    ueba
    -0.06
     UNU
    -0.06
    POSITIVE LOGITS
     styles
    0.06
     length
    0.06
     stretch
    0.06
    enever
    0.06
     Astroph
    0.06
     период
    0.06
     guarded
    0.06
     frame
    0.06
     stretched
    0.06
     comedian
    0.06
    Act Density 0.012%

    No Known Activations