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

    Neuronpedia

    INDEX
    Explanations

    buoyant force, parkour, inscription, watermarking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.05
    3
    1.05
    สัตว์
    1.05
     Département
    1.01
    2
    0.99
    1
    0.98
     Sains
    0.96
     ¿
    0.95
     xyz
    0.94
     informática
    0.94
    POSITIVE LOGITS
     and
    1.13
     방식
    0.97
    aktoren
    0.91
    坷
    0.90
    atre
    0.89
    ces
    0.88
     magnitudes
    0.88
    ppure
    0.87
    мога
    0.86
    pn
    0.86
    Act Density 0.206%

    No Known Activations