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

    Neuronpedia

    INDEX
    Explanations

    condescending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jeg
    0.84
     ड्राई
    0.77
     dry
    0.74
    ключа
    0.73
     annotate
    0.72
     Annot
    0.72
    gesetzt
    0.72
     sade
    0.71
    但不
    0.70
    ette
    0.70
    POSITIVE LOGITS
    films
    0.76
     बुध
    0.69
     পুর্ব
    0.67
    Racing
    0.67
     জর
    0.67
    former
    0.66
    Policy
    0.66
    pid
    0.64
    versions
    0.64
    okhlov
    0.64
    Act Density 0.000%

    No Known Activations