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

    Neuronpedia

    INDEX
    Explanations

    email protocols like SMTP, POP3, IMAP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.75
    NA
    0.73
    in
    0.70
    On
    0.68
    Id
    0.66
    ade
    0.64
    IN
    0.64
    ir
    0.63
    AZ
    0.62
    M
    0.61
    POSITIVE LOGITS
    thirty
    0.61
    ಾರ್
    0.61
    setUsername
    0.58
    turtle
    0.57
    seag
    0.57
     були
    0.57
    えられる
    0.57
     ಬಹು
    0.56
     चैंपियनशिप
    0.55
    ್ರಿ
    0.55
    Act Density 0.006%

    No Known Activations