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

    Neuronpedia

    INDEX
    Explanations

    combinatorics problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vinces
    -0.07
    Facade
    -0.07
     hence
    -0.06
     앉
    -0.06
    πί
    -0.06
     traits
    -0.06
    analyze
    -0.06
    二十
    -0.06
    $out
    -0.06
    Median
    -0.06
    POSITIVE LOGITS
     cambi
    0.08
     française
    0.06
    razione
    0.06
     assembler
    0.06
    -se
    0.06
     café
    0.06
    UNIT
    0.06
     din
    0.06
    .cards
    0.06
    KNOWN
    0.06
    Act Density 0.009%

    No Known Activations