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

    Neuronpedia

    INDEX
    Explanations

    listing items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ́p
    0.50
    گرام
    0.49
    ataire
    0.48
    inairement
    0.48
    داری
    0.47
    AutoStabilise
    0.46
    angulo
    0.45
    padă
    0.45
    netflix
    0.44
    peliculas
    0.44
    POSITIVE LOGITS
     Cat
    0.54
     Ammonia
    0.53
     I
    0.52
     Bees
    0.50
     trained
    0.50
     intermitt
    0.50
     requirement
    0.49
     Divide
    0.49
     Midd
    0.48
     Problem
    0.47
    Act Density 0.001%

    No Known Activations