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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    なのだ
    -0.07
    わか
    -0.06
     thinkers
    -0.06
    acker
    -0.06
    глав
    -0.06
     filmy
    -0.06
    yrıca
    -0.06
     באר
    -0.06
     Blazers
    -0.06
    싶
    -0.06
    POSITIVE LOGITS
    中药材
    0.07
    不清楚
    0.07
     컴퓨터
    0.07
    وات
    0.07
    .Complete
    0.07
    keys
    0.07
    Sparse
    0.07
     Bot
    0.07
     sunt
    0.06
     RE
    0.06
    Act Density 0.058%

    No Known Activations