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

    Neuronpedia

    INDEX
    Explanations

    time indicators (AM/PM)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lini
    0.75
     carries
    0.72
     overlooks
    0.68
     runs
    0.67
     protop
    0.66
    拥
    0.66
    /
    0.66
     continuum
    0.64
     then
    0.63
     fully
    0.63
    POSITIVE LOGITS
    ்டர்
    0.84
    ({{
    0.80
    తలు
    0.78
    CHU
    0.78
    ЕНИЕ
    0.77
    ✧
    0.77
    ब्द
    0.77
    ఎఫ్
    0.76
    risome
    0.76
    뤄
    0.75
    Act Density 0.008%

    No Known Activations