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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sentence
    -0.07
     discipl
    -0.07
     السم
    -0.07
     несколько
    -0.06
    ifique
    -0.06
    elles
    -0.06
    _outputs
    -0.06
    Only
    -0.06
     ألف
    -0.06
    -tooltip
    -0.06
    POSITIVE LOGITS
     cycl
    0.06
    炸
    0.06
     openFileDialog
    0.06
     sigue
    0.06
     hỏi
    0.06
    akra
    0.06
    alış
    0.06
    -pic
    0.06
    VML
    0.06
    þ
    0.06
    Act Density 0.004%

    No Known Activations