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

    Neuronpedia

    INDEX
    Explanations

    Ade, Trader, pubs, hard, limited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     =>
    0.45
     menampilkan
    0.45
     હતા
    0.44
     wen
    0.43
     grupa
    0.43
     dolphin
    0.42
     náklady
    0.41
     cath
    0.40
     joka
    0.40
     ž
    0.40
    POSITIVE LOGITS
    áte
    0.52
    تے
    0.50
    지에
    0.49
    CND
    0.48
    !">
    0.48
     immediacy
    0.48
    л
    0.47
     তারিখে
    0.46
    ل
    0.46
     emissivity
    0.46
    Act Density 0.000%

    No Known Activations