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

    Neuronpedia

    INDEX
    Explanations

    Math combinatorics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brennan
    -0.09
     Issues
    -0.09
     tất
    -0.08
     "'"
    -0.08
     faker
    -0.08
    faker
    -0.08
     absolument
    -0.08
     Laval
    -0.07
     seluruh
    -0.07
     /\.(
    -0.07
    POSITIVE LOGITS
     ambiguous
    0.09
     directional
    0.08
     distinguished
    0.08
    여
    0.08
     official
    0.08
    clar
    0.08
     ambiguity
    0.07
    ഗ
    0.07
    It's
    0.07
     Los
    0.07
    Act Density 0.062%

    No Known Activations