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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Core
    -0.07
     Confeder
    -0.07
     무엇
    -0.07
    ?>
↵
↵
    -0.07
     ｀
    -0.07
    嗎
    -0.06
     což
    -0.06
     suffers
    -0.06
     พฤศจ
    -0.06
     unseren
    -0.06
    POSITIVE LOGITS
    uestas
    0.07
     энерг
    0.06
    EAR
    0.06
    ्वय
    0.06
    Guardar
    0.06
    _VENDOR
    0.06
    ريع
    0.06
     Paso
    0.06
    _${
    0.06
    ालक
    0.06
    Act Density 0.031%

    No Known Activations