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

    Neuronpedia

    INDEX
    Explanations

    Names/Biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xlsx
    -0.07
     prote
    -0.06
     StartTime
    -0.06
     honoured
    -0.06
     муж
    -0.06
     nouveau
    -0.06
        ↵
    -0.06
    搞
    -0.06
     Muscle
    -0.06
    >".
    -0.05
    POSITIVE LOGITS
     AST
    0.07
     league
    0.07
    -ли
    0.06
     Unfortunately
    0.06
     Rever
    0.06
    HELL
    0.06
    ogram
    0.06
    Ho
    0.06
    isel
    0.06
     Hmm
    0.06
    Act Density 0.315%

    No Known Activations