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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WF
    -0.07
    _on
    -0.07
    亡
    -0.07
    unger
    -0.07
    ovou
    -0.06
     Tik
    -0.06
    uiten
    -0.06
     sürdür
    -0.06
     manžel
    -0.06
    арч
    -0.06
    POSITIVE LOGITS
     instanceof
    0.06
    $$
    0.06
    (pack
    0.06
    ))^
    0.06
    )<<
    0.06
    (stderr
    0.06
    ]()
    0.06
     gọi
    0.06
    .Release
    0.06
    //-----------------------------------------------------------------------------↵
    0.06
    Act Density 0.206%

    No Known Activations