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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    113
    -0.06
    aed
    -0.06
     strongly
    -0.06
     Tai
    -0.06
     Німеч
    -0.06
                ↵↵
    -0.06
    疫
    -0.06
    (state
    -0.06
    Sci
    -0.06
    ưng
    -0.06
    POSITIVE LOGITS
    ंभ
    0.07
     perpetrated
    0.06
     náklady
    0.06
    кас
    0.06
     کش
    0.06
    kj
    0.06
    부분
    0.06
     لینک
    0.06
     रह
    0.06
    ifth
    0.06
    Act Density 0.001%

    No Known Activations