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

    Neuronpedia

    INDEX
    Explanations

    section below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    及び
    0.42
     وم
    0.42
    歟
    0.42
     אשר
    0.42
    欤
    0.42
     ਅਤੇ
    0.41
     propylene
    0.40
    0.39
    ٹو
    0.39
    佰
    0.39
    POSITIVE LOGITS
     above
    0.55
     below
    0.54
     section
    0.47
     later
    0.47
     hereof
    0.41
    below
    0.40
    at
    0.40
    section
    0.40
     выше
    0.40
     úpl
    0.40
    Act Density 0.030%

    No Known Activations