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

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ویژگی
    -0.07
     контроль
    -0.06
     broadband
    -0.06
     axios
    -0.06
     widespread
    -0.06
     Transition
    -0.06
     transition
    -0.06
    .Quit
    -0.06
     Apart
    -0.06
     qualifiers
    -0.06
    POSITIVE LOGITS
    ляти
    0.07
    essim
    0.07
    tat
    0.07
    reur
    0.06
     EditorGUI
    0.06
    bos
    0.06
    oreal
    0.06
    __((
    0.06
    될
    0.06
     <$
    0.06
    Act Density 0.023%

    No Known Activations