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

    Neuronpedia

    INDEX
    Explanations

    Member

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Name
    -0.07
     החד
    -0.07
    -mediated
    -0.07
    RG
    -0.06
    公布了
    -0.06
    _FMT
    -0.06
    ปกครอง
    -0.06
     pouch
    -0.06
    MEMORY
    -0.06
     prec
    -0.06
    POSITIVE LOGITS
    مق
    0.07
    om
    0.07
    怡
    0.07
    overall
    0.07
    ophon
    0.07
     Rolled
    0.07
     messages
    0.07
    mal
    0.06
     fallback
    0.06
    ieder
    0.06
    Act Density 0.008%

    No Known Activations