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

    Neuronpedia

    INDEX
    Explanations

    moderation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acquaint
    -0.08
    รว
    -0.08
     inevitably
    -0.08
     א
    -0.07
     dedicate
    -0.07
     kali
    -0.07
     остав
    -0.07
     URLs
    -0.07
     mamy
    -0.07
     بريد
    -0.07
    POSITIVE LOGITS
     categorical
    0.09
     Roch
    0.09
     mediation
    0.09
     moderators
    0.08
     göstər
    0.08
     Mõ
    0.08
     gerçekleş
    0.08
     wyjątk
    0.08
     moderator
    0.08
    주는
    0.07
    Act Density 0.004%

    No Known Activations