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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ็นท
    -0.07
    Ａ
    -0.07
     خاطر
    -0.06
    已
    -0.06
     ucfirst
    -0.06
    _instructions
    -0.06
     negatives
    -0.06
    一定
    -0.06
     verilen
    -0.06
     تد
    -0.06
    POSITIVE LOGITS
    .")]↵
    0.07
    ogens
    0.06
    .avg
    0.06
    ()]);↵
    0.06
    .ly
    0.06
     Domestic
    0.06
     BAR
    0.06
     bur
    0.06
     scent
    0.06
     Toxic
    0.06
    Act Density 0.015%

    No Known Activations