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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rpm
    -0.07
    USER
    -0.07
    obsolete
    -0.07
    lerdi
    -0.06
     ZeroConstructor
    -0.06
     удив
    -0.06
     ум
    -0.06
    punkt
    -0.06
    凉
    -0.06
    fang
    -0.06
    POSITIVE LOGITS
    (tk
    0.08
    ($('.
    0.07
     tofu
    0.07
    (err
    0.06
    ("&
    0.06
    .database
    0.06
     mt
    0.06
     sets
    0.06
     히
    0.06
    (secret
    0.06
    Act Density 0.012%

    No Known Activations