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

    Neuronpedia

    INDEX
    Explanations

    URLs and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    착
    0.70
    스로
    0.65
    undet
    0.64
    শুভ
    0.64
    Dead
    0.64
    outh
    0.64
    ție
    0.63
    Seq
    0.62
    usetzen
    0.61
     Easily
    0.61
    POSITIVE LOGITS
     principles
    0.94
     curricula
    0.91
     seminars
    0.90
     informacije
    0.89
     informativo
    0.89
     conceptos
    0.87
     informativa
    0.84
     organiza
    0.83
     Informationen
    0.82
     curriculum
    0.82
    Act Density 0.066%

    No Known Activations