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

    Neuronpedia

    INDEX
    Explanations

    Linguistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оди
    -0.06
    стве
    -0.06
    isk
    -0.06
    “If
    -0.06
    Expect
    -0.06
     naprost
    -0.06
    ique
    -0.06
    ré
    -0.06
    卻
    -0.06
     forged
    -0.06
    POSITIVE LOGITS
     اخلاق
    0.07
    ноз
    0.07
     Ukr
    0.07
    <=$
    0.06
     korun
    0.06
    .desktop
    0.06
     हमल
    0.06
    ropol
    0.06
     ControllerBase
    0.06
    ?>/
    0.06
    Act Density 0.068%

    No Known Activations