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

    Neuronpedia

    INDEX
    Explanations

    race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fakt
    -0.07
     And
    -0.06
    _HIDE
    -0.06
     fusion
    -0.06
    .Guid
    -0.06
    .Usuario
    -0.06
     nutzen
    -0.06
    ❃
    -0.06
    あって
    -0.06
     ※
    -0.06
    POSITIVE LOGITS
     onClose
    0.07
    뿅
    0.07
    (fh
    0.07
    梢
    0.07
    깟
    0.07
    农田
    0.07
    -depth
    0.06
    (BigInteger
    0.06
    匮
    0.06
     ک
    0.06
    Act Density 0.011%

    No Known Activations