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

    Neuronpedia

    INDEX
    Explanations

    mathematical and textual concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transgression
    0.43
    ούν
    0.42
     drain
    0.41
    ğinin
    0.40
     pathways
    0.39
    Kv
    0.39
     público
    0.39
    Regarding
    0.38
    drain
    0.38
     kwargs
    0.38
    POSITIVE LOGITS
     Couleur
    0.48
     caoutch
    0.47
     Choisissez
    0.47
     Canvas
    0.44
     poumon
    0.44
     camisetas
    0.43
     nieruch
    0.43
     kleuren
    0.43
     экране
    0.42
     jaunâtre
    0.42
    Act Density 0.003%

    No Known Activations