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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.76
    in
    0.75
    ল
    0.72
     s
    0.68
    zsche
    0.64
    ac
    0.61
    zid
    0.61
    ר
    0.60
    ihe
    0.59
    ல்
    0.58
    POSITIVE LOGITS
     is
    1.05
     дней
    0.71
    날
    0.69
     روز
    0.67
    日前
    0.67
    か
    0.66
     а
    0.66
    な
    0.66
    േക്ക്
    0.66
     آنے
    0.65
    Act Density 0.435%

    No Known Activations