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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    خوان
    -0.07
     clinical
    -0.06
     Titanium
    -0.06
     фах
    -0.06
     імен
    -0.06
    赤
    -0.06
    感情
    -0.06
     Bag
    -0.06
     hoops
    -0.06
    енную
    -0.06
    POSITIVE LOGITS
    (conv
    0.07
     Ng
    0.06
     spo
    0.06
     Při
    0.06
    (Channel
    0.06
     vows
    0.06
     della
    0.06
    HB
    0.06
    以
    0.06
    @Configuration
    0.06
    Act Density 0.581%

    No Known Activations