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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    氾
    -0.07
    تدخل
    -0.07
     paw
    -0.07
     chess
    -0.07
     circulation
    -0.07
    ﳐ
    -0.07
     stall
    -0.07
    globals
    -0.07
     axial
    -0.06
    ᐢ
    -0.06
    POSITIVE LOGITS
    'http
    0.08
    apatkan
    0.07
    _cre
    0.07
    Moder
    0.07
    (piece
    0.07
    造林
    0.07
    зык
    0.07
     ähnlich
    0.06
     dozens
    0.06
    иде
    0.06
    Act Density 0.002%

    No Known Activations