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

    Neuronpedia

    INDEX
    Explanations

    python `__init__` method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réelle
    0.61
     dacă
    0.60
     estime
    0.60
     أف
    0.59
     consider
    0.58
     entrée
    0.58
     feature
    0.58
     villa
    0.58
     față
    0.57
     consideran
    0.57
    POSITIVE LOGITS
    did
    0.66
    Because
    0.61
    Construction
    0.58
    Professional
    0.56
    because
    0.56
    Ust
    0.55
    electro
    0.55
    Did
    0.54
    Inst
    0.54
    isotopes
    0.54
    Act Density 0.041%

    No Known Activations