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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     清
    -0.08
    )<<
    -0.08
    ällt
    -0.07
    ább
    -0.07
    mayacak
    -0.07
     произ
    -0.07
     sans
    -0.06
     __
    -0.06
     başlar
    -0.06
     Sms
    -0.06
    POSITIVE LOGITS
     find
    0.06
     another
    0.06
     a
    0.06
    art
    0.06
    .↵↵
    0.06
    -alist
    0.06
     finds
    0.06
     married
    0.06
    .movies
    0.06
     Amnesty
    0.06
    Act Density 0.023%

    No Known Activations