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
     portable
    -0.07
     administrations
    -0.06
     آش
    -0.06
     فال
    -0.06
     pancakes
    -0.06
    地下
    -0.06
     microseconds
    -0.06
    _Target
    -0.06
    ogh
    -0.06
    .copy
    -0.06
    POSITIVE LOGITS
     kní
    0.07
    昨
    0.06
    Japan
    0.06
     Wealth
    0.06
     použí
    0.06
     обычно
    0.06
     松
    0.06
    Pat
    0.06
    _allocate
    0.06
     occupations
    0.06
    Act Density 0.004%

    No Known Activations