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

    Neuronpedia

    INDEX
    Explanations

    leading or overseeing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ident
    0.45
    fi
    0.41
     Regul
    0.41
     计算
    0.41
     lãnh
    0.40
     códigos
    0.40
    estro
    0.40
    ieres
    0.40
    ছের
    0.40
     inversa
    0.39
    POSITIVE LOGITS
     renovations
    0.43
     выполнение
    0.43
    Camb
    0.43
     renovation
    0.42
     NSMutableArray
    0.42
    একটি
    0.42
    Airbnb
    0.42
     reforestation
    0.41
     процесс
    0.41
    トライ
    0.41
    Act Density 0.025%

    No Known Activations