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

    Neuronpedia

    INDEX
    Explanations

    names and related details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    도
    0.66
    조
    0.63
    사업
    0.57
    자
    0.57
    성
    0.57
     मानचित्र
    0.56
    장
    0.55
    지의
    0.55
    უნქ
    0.54
    も
    0.52
    POSITIVE LOGITS
    h
    0.66
    y
    0.55
    im
    0.54
    pita
    0.51
     et
    0.50
     ApJ
    0.48
    tak
    0.48
    sni
    0.48
     ET
    0.47
    mard
    0.47
    Act Density 0.000%

    No Known Activations