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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _median
    -0.07
    降
    -0.06
     kinetics
    -0.06
     分
    -0.06
    language
    -0.06
     remembers
    -0.06
    jit
    -0.06
    价值
    -0.06
    ovní
    -0.06
     Finite
    -0.06
    POSITIVE LOGITS
    陶
    0.07
    DF
    0.07
    df
    0.07
     Tur
    0.06
    .SetFloat
    0.06
    orical
    0.06
    нами
    0.06
     выб
    0.06
     Б
    0.06
     styl
    0.06
    Act Density 0.004%

    No Known Activations