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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rugby
    -0.07
     Vista
    -0.06
    ूक
    -0.06
    웨
    -0.06
    oor
    -0.06
    stice
    -0.06
    ’l
    -0.06
    ใ
    -0.06
     he
    -0.06
    鲁
    -0.06
    POSITIVE LOGITS
    _len
    0.07
     :|
    0.07
    щают
    0.07
    .done
    0.06
     bats
    0.06
     Mur
    0.06
    wolf
    0.06
     advers
    0.06
    olini
    0.06
     Микола
    0.06
    Act Density 0.099%

    No Known Activations