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

    Neuronpedia

    INDEX
    Explanations

    advertising, risk, agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.46
     Programming
    0.45
    Product
    0.45
     सॉल्यू
    0.43
     Localization
    0.43
    That
    0.43
     salads
    0.42
    m
    0.42
     Exposure
    0.41
    src
    0.41
    POSITIVE LOGITS
     pag
    0.41
    RESOURCE
    0.41
    REP
    0.41
     tillbaka
    0.40
    род
    0.39
     চ
    0.38
    ቭ
    0.38
    jährigen
    0.38
    รับ
    0.38
    らう
    0.37
    Act Density 0.000%

    No Known Activations