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

    Neuronpedia

    INDEX
    Explanations

    statutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McK
    -0.08
    Ross
    -0.07
     dangling
    -0.07
     crispy
    -0.07
    Child
    -0.07
     dire
    -0.07
    Thirty
    -0.07
    ()"↵
    -0.06
     angry
    -0.06
     Jazz
    -0.06
    POSITIVE LOGITS
    κει
    0.06
    τια
    0.06
     decltype
    0.06
    _BOOL
    0.06
    申博
    0.06
     dlou
    0.06
     unlike
    0.06
    THOOK
    0.06
    (DBG
    0.06
     plage
    0.06
    Act Density 0.013%

    No Known Activations