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

    Neuronpedia

    INDEX
    Explanations

    clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “How
    -0.06
     Degree
    -0.06
     ultimate
    -0.06
     Floating
    -0.06
    .toggle
    -0.06
     Painting
    -0.06
    lut
    -0.06
    (Texture
    -0.06
    .cuda
    -0.06
    -0.06
    POSITIVE LOGITS
     OCI
    0.07
     Avust
    0.07
    abit
    0.07
    بینی
    0.07
     xnxx
    0.06
    habit
    0.06
    ]);
↵
↵
    0.06
    ");
↵
↵
    0.06
    ALLENG
    0.06
    طه
    0.06
    Act Density 0.125%

    No Known Activations