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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onBind
    -0.07
     opioids
    -0.06
    	utils
    -0.06
    �
    -0.06
    *q
    -0.06
     Amit
    -0.06
     Lucia
    -0.06
    -tank
    -0.06
    -ch
    -0.06
    ніше
    -0.06
    POSITIVE LOGITS
     specifying
    0.07
    extensions
    0.07
    ences
    0.07
     implying
    0.07
    Listening
    0.07
    Make
    0.06
    ละคร
    0.06
     cause
    0.06
    Definitions
    0.06
     USER
    0.06
    Act Density 0.000%

    No Known Activations