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

    Neuronpedia

    INDEX
    Explanations

    definitions of "good"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    âtel
    0.40
    iles
    0.40
    ö
    0.39
    rol
    0.39
    ‌ర్
    0.38
    irk
    0.37
    6
    0.37
    일에
    0.36
    rel
    0.36
    9
    0.36
    POSITIVE LOGITS
     esta
    0.53
     the
    0.48
     essais
    0.47
     obten
    0.46
     patrocin
    0.46
     proyectos
    0.45
     त
    0.44
     dieser
    0.44
     Mitarbeiter
    0.44
     eben
    0.44
    Act Density 0.526%

    No Known Activations