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

    Neuronpedia

    INDEX
    Explanations

    viewpoint or source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вариант
    0.42
     подключа
    0.38
    ec
    0.38
    ிருக்கும்
    0.38
    ettivo
    0.38
    riterien
    0.38
    ენ
    0.37
    시오
    0.36
     রাখে
    0.36
     downloading
    0.36
    POSITIVE LOGITS
     standpoint
    1.27
     vantage
    1.16
     sources
    0.93
     perspective
    0.88
     ጋር
    0.88
     በላይ
    0.81
     источников
    0.78
    sources
    0.77
    的角度
    0.76
     fuentes
    0.75
    Act Density 0.028%

    No Known Activations