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

    Neuronpedia

    INDEX
    Explanations

    software formatting instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    олнение
    -0.08
     liquid
    -0.08
    سلام
    -0.08
     cultuur
    -0.08
    xae
    -0.08
    546
    -0.08
    ‌↵↵
    -0.08
    858
    -0.07
    .used
    -0.07
     redemption
    -0.07
    POSITIVE LOGITS
     anunciou
    0.08
     submenu
    0.08
    (gca
    0.08
    starter
    0.08
     faire
    0.08
     kompl
    0.08
     embell
    0.08
     reprendre
    0.08
     komplik
    0.08
    -arrow
    0.08
    Act Density 0.003%

    No Known Activations