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

    Neuronpedia

    INDEX
    Explanations

    thanks for sharing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.68
    uation
    0.60
    iances
    0.58
    ului
    0.58
    itance
    0.57
    utions
    0.54
    illin
    0.54
    idencia
    0.54
     Pediatric
    0.53
    od
    0.53
    POSITIVE LOGITS
     pubblici
    0.66
     hôtels
    0.64
     océ
    0.64
     publiés
    0.64
     públicos
    0.63
     œufs
    0.63
     écrire
    0.62
     oiseaux
    0.61
    ру
    0.61
     época
    0.61
    Act Density 0.003%

    No Known Activations