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

    Neuronpedia

    INDEX
    Explanations

    for loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gă
    0.86
    ATIC
    0.77
     outdated
    0.76
     giphy
    0.75
     vaccines
    0.74
     Vaccination
    0.73
     jobless
    0.73
     Viruses
    0.73
     Workplace
    0.73
     contraception
    0.73
    POSITIVE LOGITS
    راً
    0.80
    Asimismo
    0.72
    DialogInterface
    0.70
    Fr
    0.70
    Escolh
    0.69
    Deserialize
    0.68
    pitched
    0.68
    Split
    0.68
    耐久
    0.68
    خ
    0.66
    Act Density 0.000%

    No Known Activations