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

    Neuronpedia

    INDEX
    Explanations

    Eastern European/Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三三
    -0.08
    ΟΛ
    -0.07
     le
    -0.06
    全
    -0.06
     W
    -0.06
     LAST
    -0.06
    83
    -0.06
     sampler
    -0.06
    !↵↵↵↵↵↵
    -0.06
    ū
    -0.06
    POSITIVE LOGITS
     caption
    0.07
    StreamWriter
    0.06
    -container
    0.06
    _response
    0.06
    (machine
    0.06
    Integral
    0.06
    �
    0.06
     alınan
    0.06
    TASK
    0.06
    .Val
    0.06
    Act Density 0.051%

    No Known Activations