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

    Neuronpedia

    INDEX
    Explanations

    constrained instructions/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ampler
    -0.08
     mesi
    -0.08
    eux
    -0.08
    著
    -0.08
     필요한
    -0.08
     בהת
    -0.08
     중요
    -0.07
     cpf
    -0.07
     måneder
    -0.07
     Banker
    -0.07
    POSITIVE LOGITS
     제외
    0.11
     ഒഴിവ
    0.09
     verzichten
    0.09
     unless
    0.09
    unless
    0.09
    は禁止
    0.09
    /Navbar
    0.08
     ahubwo
    0.08
     larvae
    0.08
     lar
    0.08
    Act Density 0.058%

    No Known Activations