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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    المكان
    -0.69
     Rais
    -0.63
     Signalez
    -0.63
    зулта
    -0.62
    MockMvc
    -0.62
    ImageField
    -0.59
    AxisAlignment
    -0.58
    المشاركات
    -0.57
     writeTo
    -0.57
    DOCTYPE
    -0.57
    POSITIVE LOGITS
     bar
    0.52
    InputTagHelper
    0.46
     tipped
    0.43
    bar
    0.42
     coroa
    0.42
    ム
    0.41
     re
    0.40
    stw
    0.40
     k
    0.39
     Bar
    0.39
    Act Density 0.001%

    No Known Activations