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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multiplier
    -0.07
    assemble
    -0.07
    Chair
    -0.06
     SPR
    -0.06
     Centers
    -0.06
     καν
    -0.06
    Luc
    -0.06
     支
    -0.06
    	constructor
    -0.06
     thiên
    -0.06
    POSITIVE LOGITS
    ISE
    0.07
    fur
    0.07
    mlink
    0.06
    ))
↵
↵
    0.06
    Auf
    0.06
    >";↵
    0.06
    )):
    0.06
     مرتب
    0.06
    腦
    0.06
          ↵      ↵
    0.06
    Act Density 0.000%

    No Known Activations