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

    Neuronpedia

    INDEX
    Explanations

    explaining how something works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خواهد
    0.33
     signup
    0.31
     score
    0.31
     ('
    0.30
     وب
    0.30
     நிச்சயம்
    0.29
    ിയെ
    0.29
     slope
    0.29
     side
    0.29
     respiration
    0.29
    POSITIVE LOGITS
    CONDS
    0.35
    rzed
    0.33
    aliers
    0.32
    ל
    0.32
    ARDO
    0.31
    ，《
    0.30
     jeudi
    0.30
     mardi
    0.30
     esigen
    0.30
    aderos
    0.30
    Act Density 0.000%

    No Known Activations