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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     유형
    -0.07
     cultivated
    -0.06
     Cherry
    -0.06
     утеп
    -0.06
    ectl
    -0.06
     SECURITY
    -0.06
     sonra
    -0.06
     Firearms
    -0.06
    _drag
    -0.06
     lunches
    -0.06
    POSITIVE LOGITS
    cho
    0.08
    一步
    0.07
     作
    0.07
     Delhi
    0.07
     contracted
    0.06
     guesses
    0.06
    �
    0.06
    gesture
    0.06
     standout
    0.06
     muted
    0.06
    Act Density 0.002%

    No Known Activations