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

    Neuronpedia

    INDEX
    Explanations

    very end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DTS
    0.62
     TRIG
    0.60
     ETL
    0.57
     GAS
    0.57
     dolayı
    0.55
    CTOGRAM
    0.55
     HA
    0.55
     ETS
    0.55
     APPLY
    0.55
     DAM
    0.54
    POSITIVE LOGITS
    im
    0.72
    ro
    0.62
    en
    0.59
    use
    0.57
    ued
    0.56
    hue
    0.55
    year
    0.54
    op
    0.54
    Rae
    0.54
    other
    0.53
    Act Density 0.003%

    No Known Activations