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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azon
    -0.07
     trousers
    -0.07
    essaging
    -0.07
     expiration
    -0.07
    引用频次
    -0.06
     chromium
    -0.06
    _lhs
    -0.06
     alcoholic
    -0.06
    틴
    -0.06
     potentials
    -0.06
    POSITIVE LOGITS
     pwm
    0.07
     Perfect
    0.07
    Unique
    0.07
    '},
↵
    0.06
    xbb
    0.06
     Elijah
    0.06
    ]):
↵
    0.06
     ]),↵
    0.06
    =l
    0.06
     tro
    0.06
    Act Density 0.026%

    No Known Activations