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

    Neuronpedia

    INDEX
    Explanations

    clase subclass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ингреди
    0.48
    SpringMVCProject
    0.46
     oes
    0.44
     הייתה
    0.41
    archiwizowane
    0.41
     دونك
    0.41
     vacances
    0.40
     معاملہ
    0.39
     ليك
    0.39
     arrib
    0.38
    POSITIVE LOGITS
     uncomment
    0.52
     subclass
    0.49
     Uncomment
    0.47
     XML
    0.47
     Play
    0.45
     scenarios
    0.45
     subclasses
    0.44
     Launch
    0.44
     However
    0.44
     scenario
    0.44
    Act Density 0.001%

    No Known Activations