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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Functional
    -0.07
    🗣
    -0.07
     sells
    -0.07
     służ
    -0.07
    ennon
    -0.07
     какой
    -0.06
     superst
    -0.06
     школь
    -0.06
    违约
    -0.06
    蹿
    -0.06
    POSITIVE LOGITS
     Sid
    0.08
    -President
    0.07
    翦
    0.07
     pantry
    0.07
    삭
    0.07
    (vec
    0.07
    蓠
    0.06
    حد
    0.06
     Gear
    0.06
     помещения
    0.06
    Act Density 0.002%

    No Known Activations