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

    Neuronpedia

    INDEX
    Explanations

    primary stress in phonetic transcriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    0.94
     in
    0.93
    り
    0.89
    ל
    0.85
    ח
    0.85
     is
    0.79
     manure
    0.79
     t
    0.75
    ש
    0.75
    ไม่
    0.74
    POSITIVE LOGITS
    ase
    0.88
    asan
    0.85
    asa
    0.81
    one
    0.80
    rok
    0.80
    acija
    0.76
    asjoner
    0.75
    aria
    0.75
    ungs
    0.75
    at
    0.74
    Act Density 0.001%

    No Known Activations