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

    Neuronpedia

    INDEX
    Explanations

    Diego

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pher
    -0.08
    ，一
    -0.07
    くらい
    -0.07
    _branch
    -0.07
     glamorous
    -0.07
     Кар
    -0.07
     cultivate
    -0.07
    :@
    -0.06
     medications
    -0.06
    istributions
    -0.06
    POSITIVE LOGITS
     Diego
    0.31
    iego
    0.09
     Cubs
    0.08
     Spokane
    0.07
     bathing
    0.07
    go
    0.07
    ugo
    0.07
     DIE
    0.07
    ogo
    0.06
     saddle
    0.06
    Act Density 0.002%

    No Known Activations