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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arena
    -0.08
     trenutno
    -0.08
     '**
    -0.07
    quant
    -0.07
    metics
    -0.07
    keta
    -0.07
    mq
    -0.07
    wr
    -0.07
    atica
    -0.07
     arbitr
    -0.07
    POSITIVE LOGITS
     важ
    0.10
     sariling
    0.09
     gné
    0.09
     карда
    0.09
     וואָ
    0.09
    таи
    0.09
     avei
    0.09
     кардааст
    0.09
     намуд
    0.09
     приключ
    0.09
    Act Density 0.114%

    No Known Activations