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

    Neuronpedia

    INDEX
    Explanations

    time lengths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Descri
    -0.07
    module
    -0.06
    	module
    -0.06
    TU
    -0.06
    cov
    -0.06
    weeney
    -0.06
    _VEC
    -0.06
    Mas
    -0.06
    VEST
    -0.06
    ADA
    -0.06
    POSITIVE LOGITS
     dlouho
    0.07
     Familie
    0.07
    žití
    0.07
     Silver
    0.07
     pots
    0.06
     PageSize
    0.06
    ські
    0.06
    .BackgroundColor
    0.06
     版
    0.06
     ediyorum
    0.06
    Act Density 0.027%

    No Known Activations