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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (LocalDate
    -0.07
    attice
    -0.07
     انقلاب
    -0.07
    (tp
    -0.06
    ｧ
    -0.06
    ині
    -0.06
     RouteServiceProvider
    -0.06
    _VOICE
    -0.06
    ۱۶
    -0.06
    _AND
    -0.06
    POSITIVE LOGITS
     Marg
    0.06
     WH
    0.06
    .obs
    0.06
     рід
    0.06
    Drag
    0.06
     hoc
    0.06
     marg
    0.06
     FL
    0.06
     drained
    0.06
     Roo
    0.06
    Act Density 0.112%

    No Known Activations