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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    磨
    -0.07
    席
    -0.07
     strongest
    -0.06
     Powerful
    -0.06
    練
    -0.06
     דין
    -0.06
    ⾨
    -0.06
    addle
    -0.06
    潖
    -0.06
    ᵉ
    -0.06
    POSITIVE LOGITS
    ,user
    0.08
    SEA
    0.08
     사람
    0.08
     theoret
    0.07
     universal
    0.07
    _redirected
    0.07
     осуществ
    0.07
    ซา
    0.07
     chois
    0.07
    _UTF
    0.07
    Act Density 0.023%

    No Known Activations