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

    Neuronpedia

    INDEX
    Explanations

    entities and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.44
     arugula
    0.43
    🈯
    0.41
     dogs
    0.41
    aluronic
    0.41
     dụ
    0.41
    :
    0.41
     Chord
    0.40
     ulcers
    0.40
     lizards
    0.39
    POSITIVE LOGITS
    ewöhn
    0.48
     به
    0.45
     से
    0.45
    Navigation
    0.44
    羹
    0.43
    ขึ้น
    0.42
    Catch
    0.42
     تصور
    0.41
    년에
    0.41
    HttpPut
    0.41
    Act Density 0.010%

    No Known Activations