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

    Neuronpedia

    INDEX
    Explanations

    prefix + suffix compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spaper
    0.34
     calibrate
    0.33
     зуб
    0.32
     صفحه
    0.30
    spapers
    0.30
    ут
    0.30
    oretically
    0.29
    تحانات
    0.29
    ुण
    0.28
    ূনতম
    0.28
    POSITIVE LOGITS
    </strong>
    0.42
    failure
    0.34
    んでいる
    0.33
    ряду
    0.32
     માટે
    0.32
    isuus
    0.32
    ισμό
    0.31
    受到了
    0.31
     She
    0.30
     ശേഷ
    0.30
    Act Density 0.041%

    No Known Activations