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

    Neuronpedia

    INDEX
    Explanations

    definitely followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.52
    eers
    1.20
    eer
    1.14
    ição
    1.09
     presentar
    1.07
    日から
    1.07
    ių
    1.05
    iş
    1.03
     formar
    1.02
    oo
    1.02
    POSITIVE LOGITS
    д
    1.16
    за
    1.14
    ية
    1.13
    га
    1.13
    𝒑
    1.09
    ס
    1.09
    ם
    1.07
    มี
    1.05
    м
    1.05
    פ
    1.04
    Act Density 0.222%

    No Known Activations