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

    Neuronpedia

    INDEX
    Explanations

    basic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /renderer
    -0.08
     aim
    -0.07
    /")↵
    -0.07
    (obs
    -0.07
     mooie
    -0.06
     syst
    -0.06
    olare
    -0.06
    agar
    -0.06
    ілля
    -0.06
     DWORD
    -0.06
    POSITIVE LOGITS
     basic
    0.09
     Basic
    0.07
    小学
    0.07
     @$
    0.07
     조회
    0.07
     Essential
    0.06
     국민
    0.06
     mileage
    0.06
     kır
    0.06
    oby
    0.06
    Act Density 0.115%

    No Known Activations