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

    Neuronpedia

    INDEX
    Explanations

    value based on current rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ін
    0.45
    Bola
    0.44
     típico
    0.41
    getDefault
    0.41
    দাতা
    0.41
     præ
    0.40
    rugg
    0.40
    гно
    0.40
    arına
    0.39
    ита
    0.39
    POSITIVE LOGITS
     US
    0.45
     location
    0.42
    同じ
    0.42
     ഏറ്റവും
    0.42
     earliest
    0.40
    現在の
    0.40
     पटक
    0.40
     pate
    0.40
     all
    0.39
     mung
    0.39
    Act Density 0.003%

    No Known Activations