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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cleanliness
    -0.07
    delivery
    -0.07
    TeX
    -0.07
    ğın
    -0.07
    fahren
    -0.07
     yaptı
    -0.07
     VIII
    -0.06
     eas
    -0.06
     These
    -0.06
    986
    -0.06
    POSITIVE LOGITS
    <quote
    0.07
    LError
    0.06
     المست
    0.06
     gridView
    0.06
    .Preference
    0.06
    ')}>↵
    0.06
    /{$
    0.06
    Danny
    0.06
    ,unsigned
    0.06
    ignKey
    0.06
    Act Density 0.007%

    No Known Activations