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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.95
    0.73
     It
    0.68
     to
    0.65
     it
    0.63
    கள்
    0.62
    rs
    0.59
     Chinatown
    0.59
     cheeky
    0.59
    })$,
    0.57
    POSITIVE LOGITS
    ↵
    0.78
    3
    0.73
    ఆర్‌
    0.73
    ла
    0.72
    Instances
    0.69
    :
    0.68
    ৪
    0.68
    MAIL
    0.67
    irrahim
    0.67
    @
    0.66
    Act Density 0.003%

    No Known Activations