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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sampler
    -0.07
    _sampler
    -0.07
    選手
    -0.07
    writing
    -0.07
    τησε
    -0.07
    spam
    -0.06
    (del
    -0.06
    ---------↵↵
    -0.06
     معلومات
    -0.06
     kâ
    -0.06
    POSITIVE LOGITS
    택
    0.07
     Dat
    0.07
    づ
    0.07
    .sale
    0.06
     تع
    0.06
    secondary
    0.06
    assist
    0.06
     whipping
    0.06
     Hydraulic
    0.06
     cou
    0.06
    Act Density 0.001%

    No Known Activations