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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Validation
    -0.08
     mø
    -0.07
     level
    -0.06
     sondern
    -0.06
    _append
    -0.06
    ('.')↵
    -0.06
     tóc
    -0.06
    دن
    -0.06
    ()]
    -0.06
     MacOS
    -0.06
    POSITIVE LOGITS
    โร
    0.07
    (users
    0.07
    ・・・
    0.07
     ordinal
    0.06
     Этот
    0.06
     خویش
    0.06
     Hur
    0.06
     titulo
    0.06
     ducks
    0.06
    lobber
    0.06
    Act Density 0.004%

    No Known Activations