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

    Neuronpedia

    INDEX
    Explanations

    slow cooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mafia
    -0.07
    Verifier
    -0.06
    Mob
    -0.06
    transform
    -0.06
    .iso
    -0.06
     dock
    -0.06
    ランス
    -0.06
     Eye
    -0.06
    евич
    -0.06
    xBF
    -0.06
    POSITIVE LOGITS
    이를
    0.06
    \Repositories
    0.06
     точно
    0.06
     публі
    0.06
     allen
    0.06
     +#+#+#+#+#+
    0.06
     obra
    0.06
    brain
    0.06
     funky
    0.06
     exclude
    0.06
    Act Density 0.009%

    No Known Activations