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

    Neuronpedia

    INDEX
    Explanations

    xml

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    7
    -0.08
     Mend
    -0.08
     CC
    -0.07
    itus
    -0.07
    즘
    -0.07
    @Id
    -0.07
    痴
    -0.07
    诚实
    -0.07
    开设
    -0.07
    _decoder
    -0.07
    POSITIVE LOGITS
    촤
    0.08
    orary
    0.08
    Convertible
    0.07
     kayna
    0.07
     xml
    0.07
    水墨
    0.07
    ographed
    0.07
     bureaucratic
    0.07
    escaped
    0.07
    ками
    0.07
    Act Density 0.011%

    No Known Activations