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

    Neuronpedia

    INDEX
    Explanations

    Forms of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nemoc
    -0.07
     bombing
    -0.07
     Tower
    -0.06
     ortak
    -0.06
     tady
    -0.06
    now
    -0.06
     meslek
    -0.06
     secre
    -0.06
    imagin
    -0.06
    	bus
    -0.06
    POSITIVE LOGITS
    _was
    0.07
     useState
    0.06
    reds
    0.06
    NAME
    0.06
    (ID
    0.06
     엄
    0.06
     UI
    0.06
    esty
    0.06
     adventurer
    0.06
    //*[
    0.06
    Act Density 0.042%

    No Known Activations