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

    Neuronpedia

    INDEX
    Explanations

    environmental green

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     başlang
    0.61
    骡
    0.52
     Pfer
    0.51
     IDENT
    0.50
     ORGAN
    0.50
    𒉌
    0.50
    ică
    0.49
     insectes
    0.48
     Народ
    0.48
     idempot
    0.48
    POSITIVE LOGITS
    marquee
    0.49
    eteers
    0.43
    ز
    0.43
    뺨
    0.43
    odh
    0.43
    裄
    0.42
     ይህም
    0.42
    girls
    0.42
    нус
    0.41
    цене
    0.41
    Act Density 0.000%

    No Known Activations