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

    Neuronpedia

    INDEX
    Explanations

    triple backticks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erías
    -0.09
    iliy
    -0.08
    ES
    -0.08
     Pathfinder
    -0.08
    umbre
    -0.07
    “You
    -0.07
    ABET
    -0.07
    “One
    -0.07
    ġ
    -0.07
                         ↵
    -0.07
    POSITIVE LOGITS
     cess
    0.08
     ocasión
    0.08
     للت
    0.08
     donn
    0.08
     annonc
    0.07
    -toggle
    0.07
     السم
    0.07
    لن
    0.07
     annunci
    0.07
     घोष
    0.07
    Act Density 0.003%

    No Known Activations