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

    Neuronpedia

    INDEX
    Explanations

    list marker "*"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TComponent
    0.74
     চিৎ
    0.73
    動画
    0.71
     Timelapse
    0.70
    來越
    0.69
     Paar
    0.68
     ProRes
    0.68
    潮
    0.68
     popOperand
    0.68
     फड
    0.67
    POSITIVE LOGITS
     China
    0.65
     bears
    0.65
    sim
    0.63
    backed
    0.62
    arrows
    0.61
     مول
    0.61
     gelijk
    0.61
    யில
    0.61
     neque
    0.60
    сний
    0.59
    Act Density 0.039%

    No Known Activations