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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inorganic
    0.30
     tio
    0.30
     assistant
    0.29
     enterprise
    0.29
     Assistant
    0.29
     dors
    0.29
     elect
    0.28
     hydrochloric
    0.28
     hydros
    0.28
     corro
    0.28
    POSITIVE LOGITS
    और
    0.41
     और
    0.40
     ਅਤੇ
    0.36
     आणि
    0.34
     અને
    0.33
    ដៃ
    0.32
    และ
    0.31
     folgen
    0.31
     și
    0.30
     และ
    0.30
    Act Density 0.073%

    No Known Activations