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

    Neuronpedia

    INDEX
    Explanations

    "let" followed by punctuation or "have"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glTex
    0.66
     mangas
    0.65
     mutated
    0.64
     Goku
    0.64
     saludar
    0.64
     regras
    0.63
     only
    0.63
     suc
    0.63
     tylko
    0.62
     doble
    0.62
    POSITIVE LOGITS
    ocultural
    0.77
    National
    0.72
    Civil
    0.67
    Department
    0.67
     издание
    0.66
    iological
    0.65
    Cultural
    0.65
    ournal
    0.64
    Healthcare
    0.64
    Science
    0.63
    Act Density 0.017%

    No Known Activations