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
     Flames
    -0.07
    esthesia
    -0.07
     Dover
    -0.06
     Gundam
    -0.06
     alloys
    -0.06
     separator
    -0.06
    -days
    -0.06
     Wife
    -0.06
    hevik
    -0.06
     dq
    -0.06
    POSITIVE LOGITS
     �
    0.06
     부산
    0.06
    鸟
    0.06
     Lt
    0.06
     сили
    0.06
     گردید
    0.06
    clear
    0.06
    Continue
    0.06
     прибор
    0.06
     đỏ
    0.06
    Act Density 0.090%

    No Known Activations