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

    Neuronpedia

    INDEX
    Explanations

    rules and boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tertentu
    0.47
    ထ
    0.45
    $，
    0.45
    र्
    0.44
     RoHS
    0.43
    Fax
    0.42
    Netherlands
    0.42
     Umum
    0.41
    церт
    0.41
    Facilities
    0.41
    POSITIVE LOGITS
     grueling
    0.50
     జరుగు
    0.48
     capitaine
    0.46
     rampant
    0.46
     час
    0.45
     combattre
    0.44
     nac
    0.43
     twisting
    0.43
     можна
    0.43
     використову
    0.43
    Act Density 0.012%

    No Known Activations