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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to emails and mailing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    email Address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.64
     فريبيس
    -0.49
    ően
    -0.49
    +#+#
    -0.47
     للاسماء
    -0.44
     inşa
    -0.40
    ronpa
    -0.39
    orsche
    -0.39
    RTSN
    -0.39
    SubType
    -0.39
    POSITIVE LOGITS
     getEmail
    0.54
     Velas
    0.53
     itſelf
    0.52
    getEmail
    0.51
     userEmail
    0.49
     email
    0.49
     raiſ
    0.48
    setEmail
    0.47
     Email
    0.45
     ſch
    0.45
    Act Density 0.007%

    No Known Activations