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

    Neuronpedia

    INDEX
    Explanations

    say access modifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poses
    -0.07
    цю
    -0.07
    ज
    -0.07
    sWith
    -0.06
    跌
    -0.06
    off
    -0.06
     Rent
    -0.06
    /ajax
    -0.06
     whatsapp
    -0.06
     payouts
    -0.06
    POSITIVE LOGITS
    (ChatColor
    0.07
     dní
    0.07
     ChatColor
    0.07
     khung
    0.07
    แหน
    0.07
    getCell
    0.06
    Ub
    0.06
    ;br
    0.06
    ;width
    0.06
     mang
    0.06
    Act Density 0.031%

    No Known Activations