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

    Neuronpedia

    INDEX
    Explanations

    Email/web templates and structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overturned
    -0.08
     vigilancia
    -0.08
     seized
    -0.08
     mining
    -0.08
    _STARTED
    -0.07
     vertreten
    -0.07
    監
    -0.07
    .goods
    -0.07
     squat
    -0.07
     docking
    -0.07
    POSITIVE LOGITS
     unsubscribe
    0.10
    \Mail
    0.09
    Emails
    0.09
     письмо
    0.09
    邮件
    0.09
     이메일
    0.09
    	cell
    0.09
    emails
    0.09
    _mail
    0.08
    _email
    0.08
    Act Density 0.014%

    No Known Activations