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

    Neuronpedia

    INDEX
    Explanations

    <=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manipulation
    -0.07
     label
    -0.07
    NotFoundException
    -0.07
     pot
    -0.07
     Thomas
    -0.07
    attack
    -0.07
     adversary
    -0.07
    -field
    -0.07
    LC
    -0.07
     synonym
    -0.07
    POSITIVE LOGITS
    pageNum
    0.06
    Ngày
    0.06
    Produ
    0.06
    gunakan
    0.06
     ณ
    0.06
    نية
    0.06
    |--------------------------------------------------------------------------↵
    0.06
    editable
    0.06
     собой
    0.06
     могла
    0.05
    Act Density 0.002%

    No Known Activations