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

    Neuronpedia

    INDEX
    Explanations

    points, springs, mortal, Attractive, Foot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ricky
    0.58
    Truly
    0.58
     podstawie
    0.56
    美國
    0.55
     jugadores
    0.55
     ajud
    0.54
     intellectually
    0.54
     Estad
    0.54
     Stanis
    0.54
    Understand
    0.54
    POSITIVE LOGITS
     sejumlah
    0.42
     Site
    0.41
     inti
    0.41
    ከር
    0.40
     columns
    0.40
    ILIO
    0.39
     perpetrated
    0.39
     perforation
    0.38
    COUVER
    0.38
    IDUAL
    0.38
    Act Density 0.000%

    No Known Activations