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

    Neuronpedia

    INDEX
    Explanations

    sending codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     franchement
    -0.08
     malformed
    -0.08
    SETTING
    -0.08
     înainte
    -0.08
     HISTORY
    -0.08
     dyst
    -0.07
     규모
    -0.07
    .SEVERE
    -0.07
     což
    -0.07
     неправиль
    -0.07
    POSITIVE LOGITS
     emailed
    0.12
    验证码
    0.11
     भेज
    0.10
     gönder
    0.09
    Printed
    0.09
    Otp
    0.09
     મોક
    0.09
    短信
    0.09
    Sms
    0.09
    Verification
    0.09
    Act Density 0.011%

    No Known Activations