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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wouldn
    -0.08
    筹划
    -0.07
     már
    -0.07
    楒
    -0.07
    的眼
    -0.07
     insanların
    -0.07
    锝
    -0.07
     isEqual
    -0.07
    達到
    -0.07
    exercise
    -0.07
    POSITIVE LOGITS
    增幅
    0.07
    akk
    0.07
     forearm
    0.07
    Az
    0.07
    Rates
    0.07
    نمو
    0.07
    .Must
    0.07
    谓
    0.06
    '")↵
    0.06
    ailed
    0.06
    Act Density 0.016%

    No Known Activations