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

    Neuronpedia

    INDEX
    Explanations

    data- attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wonder
    -0.88
    ～～～
    -0.87
    보다
    -0.86
     wondered
    -0.84
    类
    -0.84
    wonder
    -0.81
    wanted
    -0.81
    arity
    -0.79
     Sima
    -0.75
    竄
    -0.75
    POSITIVE LOGITS
    咄
    0.86
     ciclista
    0.84
    vensis
    0.80
     municipios
    0.79
     roles
    0.77
    ดำ
    0.77
     izle
    0.77
    mă
    0.76
    ͦ
    0.75
    ▮
    0.75
    Act Density 0.021%

    No Known Activations