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

    Neuronpedia

    INDEX
    Explanations

    job, fiberglass, or effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    QL
    0.42
     treating
    0.40
     Journal
    0.40
     লাই
    0.38
    Os
    0.37
     If
    0.36
    find
    0.36
    想
    0.36
    RI
    0.36
    Qt
    0.36
    POSITIVE LOGITS
    Phrase
    0.50
     además
    0.50
     mendapat
    0.49
    솝
    0.49
     acabó
    0.48
     cliché
    0.48
     सिलेबस
    0.47
     clichés
    0.47
     została
    0.47
     insults
    0.47
    Act Density 0.007%

    No Known Activations