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

    Neuronpedia

    INDEX
    Explanations

    config

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TimeZone
    -0.07
     Originally
    -0.07
     Considering
    -0.07
    dest
    -0.07
    erg
    -0.06
     С
    -0.06
    rg
    -0.06
    少女
    -0.06
    (ARG
    -0.06
    趣
    -0.06
    POSITIVE LOGITS
     traceback
    0.07
    等活动
    0.07
    큭
    0.07
    있는
    0.06
     pays
    0.06
    ర
    0.06
     policies
    0.06
    ELLOW
    0.06
     Bryan
    0.06
     Canyon
    0.06
    Act Density 0.003%

    No Known Activations