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

    Neuronpedia

    INDEX
    Explanations

    descriptive words after "is" or "are"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.36
    Т
    0.34
    ដែល
    0.34
    ل
    0.33
    Μ
    0.32
    2
    0.31
    ш
    0.30
    У
    0.30
    ست
    0.30
    न
    0.30
    POSITIVE LOGITS
    0.40
    คัญ
    0.30
     sorely
    0.30
     unaccount
    0.30
     not
    0.29
     pourtant
    0.29
     constantly
    0.28
     ALSO
    0.27
     receivable
    0.27
    hape
    0.27
    Act Density 0.200%

    No Known Activations