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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ically
    -0.07
    实验
    -0.07
    -now
    -0.07
    Animated
    -0.07
     foss
    -0.07
    eceğiz
    -0.06
    Nos
    -0.06
    ]-->↵
    -0.06
    NST
    -0.06
     ----------------------------------------------------------------------------
    -0.06
    POSITIVE LOGITS
     Paolo
    0.06
    pone
    0.06
     yıllar
    0.06
     모집
    0.06
     مک
    0.06
    deps
    0.06
     FileAccess
    0.06
     филь
    0.05
    odb
    0.05
     Ga
    0.05
    Act Density 0.220%

    No Known Activations