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

    Neuronpedia

    INDEX
    Explanations

    pulls, hits, line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tahun
    0.82
    0.80
     years
    0.74
     undefeated
    0.74
     milestones
    0.73
     whopping
    0.73
     因为
    0.73
    Western
    0.71
    ′
    0.71
    insured
    0.71
    POSITIVE LOGITS
    riture
    0.80
    ricted
    0.80
    ሎችን
    0.78
     Create
    0.76
    ا
    0.76
    不是
    0.73
    含ま
    0.73
    ள்ளன
    0.73
    助于
    0.71
     Pública
    0.70
    Act Density 0.142%

    No Known Activations