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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seeking
    -0.08
     Cran
    -0.07
     seek
    -0.07
     ...↵↵↵
    -0.07
    Cer
    -0.07
    Eastern
    -0.07
    Classpath
    -0.07
    market
    -0.06
     unfolding
    -0.06
    Wish
    -0.06
    POSITIVE LOGITS
     respectively
    0.15
     alike
    0.15
     ஆகிய
    0.14
     respectivamente
    0.14
     соответственно
    0.13
     각각
    0.13
    分别
    0.12
     gleicher
    0.12
     എന്നീ
    0.12
     beide
    0.11
    Act Density 0.405%

    No Known Activations