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

    Neuronpedia

    INDEX
    Explanations

    email address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     치료
    0.54
    untur
    0.52
    痱
    0.52
     бактери
    0.51
     коро
    0.51
    力量
    0.50
     analges
    0.49
    𒊒
    0.48
    柺
    0.48
    ❤❤
    0.47
    POSITIVE LOGITS
     Email
    1.02
     email
    0.98
    email
    0.85
     emails
    0.85
    Email
    0.84
     Emails
    0.78
     emailing
    0.75
     correo
    0.70
    邮箱
    0.68
    EMAIL
    0.67
    Act Density 0.033%

    No Known Activations