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

    Neuronpedia

    INDEX
    Explanations

    locations and ideas

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Có
    0.69
    ன்றால்
    0.63
    వె
    0.59
    large
    0.59
    Fantastic
    0.59
    气质
    0.59
    ambo
    0.59
    vida
    0.59
    etse
    0.59
    meye
    0.58
    POSITIVE LOGITS
     slice
    0.70
     Kerry
    0.66
     الأول
    0.66
    궂
    0.63
     Agg
    0.63
     poking
    0.63
     Antioch
    0.62
     Mattress
    0.62
     Ants
    0.61
     slices
    0.60
    Act Density 0.000%

    No Known Activations