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

    Neuronpedia

    INDEX
    Explanations

    ioc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InputElement
    -0.08
     الشم
    -0.07
     punishments
    -0.07
           ↵↵
    -0.07
    ểm
    -0.07
    ाण
    -0.06
    GenericType
    -0.06
     mooie
    -0.06
    bold
    -0.06
    ("*
    -0.06
    POSITIVE LOGITS
     digital
    0.06
     Yi
    0.06
    _bl
    0.06
     дир
    0.06
     White
    0.06
    axy
    0.06
     Nik
    0.06
    byte
    0.06
     deterministic
    0.06
     dominating
    0.06
    Act Density 0.003%

    No Known Activations