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

    Neuronpedia

    INDEX
    Explanations

    lack of understanding or critical reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     görsel
    0.49
    ාවිත
    0.48
     AGRICULTURAL
    0.47
     DAIRY
    0.47
    哺乳
    0.46
     NF
    0.44
    儿子
    0.44
    醤油
    0.43
     SERIAL
    0.43
     MNRAS
    0.43
    POSITIVE LOGITS
    ل
    0.53
    level
    0.53
    l
    0.49
    c
    0.49
    Dé
    0.48
    es
    0.46
    al
    0.46
    rs
    0.46
    ਬ
    0.46
    on
    0.46
    Act Density 0.001%

    No Known Activations