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

    Neuronpedia

    INDEX
    Explanations

    potential choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    symbol
    0.79
     қа
    0.76
    yclerView
    0.75
    rensa
    0.74
     menyimpan
    0.74
    dados
    0.74
    郆
    0.73
     afficher
    0.71
    frying
    0.71
     símbolo
    0.71
    POSITIVE LOGITS
    แต่ละ
    1.00
     lựa
    0.91
     chosen
    0.91
     Potential
    0.90
     chose
    0.81
     potential
    0.80
     Each
    0.80
     each
    0.78
     각각
    0.78
     choices
    0.76
    Act Density 0.843%

    No Known Activations