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

    Neuronpedia

    INDEX
    Explanations

    8e CSS property values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     groupby
    0.42
     usually
    0.38
    ENING
    0.38
     satirical
    0.37
     sometimes
    0.37
    ወዳ
    0.37
     amps
    0.37
    ভাসের
    0.36
     typically
    0.36
    사의
    0.36
    POSITIVE LOGITS
    ụ
    0.38
    hi
    0.36
    xy
    0.36
    rik
    0.36
    ည့်
    0.35
    cz
    0.34
     dito
    0.34
    X
    0.34
    cic
    0.34
    smtb
    0.34
    Act Density 0.007%

    No Known Activations