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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unreliable
    -0.08
    >());↵↵
    -0.07
    غال
    -0.07
     ),
    -0.07
    Creators
    -0.06
    353
    -0.06
    论坛
    -0.06
     Shar
    -0.06
    ());↵↵
    -0.06
     |
    -0.06
    POSITIVE LOGITS
    xampp
    0.06
    ısından
    0.06
     ActionType
    0.06
    -engine
    0.06
     Coff
    0.06
    keleton
    0.06
    -animate
    0.06
     Sawyer
    0.06
     bakeka
    0.06
     эффек
    0.06
    Act Density 0.011%

    No Known Activations