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

    Neuronpedia

    INDEX
    Explanations

    Asking questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dickens
    -0.08
    🎩
    -0.07
     hayatı
    -0.07
    利
    -0.07
    ightly
    -0.07
    써
    -0.07
    𫔎
    -0.07
    他们都
    -0.07
    냏
    -0.06
    Minutes
    -0.06
    POSITIVE LOGITS
     echang
    0.07
     navigationOptions
    0.07
     Gan
    0.07
    涘
    0.07
    :async
    0.07
    [size
    0.07
     sä
    0.07
     footsteps
    0.07
     storyboard
    0.06
    陂
    0.06
    Act Density 0.022%

    No Known Activations