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

    Neuronpedia

    INDEX
    Explanations

    2 and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    February
    0.77
    사
    0.77
    January
    0.77
    September
    0.75
    ap
    0.74
    این
    0.70
    October
    0.69
     собы
    0.68
    ㅈ
    0.68
    November
    0.66
    POSITIVE LOGITS
     compactly
    0.77
     યોગ્ય
    0.75
     affirmations
    0.71
     blissful
    0.71
    तोंडा
    0.71
     fasteners
    0.70
    classifiers
    0.70
     introns
    0.70
     orbits
    0.69
     intoler
    0.68
    Act Density 0.001%

    No Known Activations