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

    Neuronpedia

    INDEX
    Explanations

    Book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     across
    -0.07
    posit
    -0.07
     company
    -0.07
     Graduate
    -0.07
     Project
    -0.07
     mobile
    -0.06
     vary
    -0.06
     goodies
    -0.06
     belly
    -0.06
     continued
    -0.06
    POSITIVE LOGITS
     alınan
    0.07
     preco
    0.07
     Zac
    0.07
     Ayrıca
    0.06
     @_;↵↵
    0.06
     Abb
    0.06
    ıyorum
    0.06
    §ظ
    0.06
    教学
    0.06
    ilmiştir
    0.06
    Act Density 0.034%

    No Known Activations