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

    Neuronpedia

    INDEX
    Explanations

    Mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rigid
    -0.06
    ceiver
    -0.06
    endet
    -0.06
    ighton
    -0.06
     Patient
    -0.06
     StringBuilder
    -0.06
     interior
    -0.06
     Soldiers
    -0.06
    )#
    -0.06
     hospital
    -0.06
    POSITIVE LOGITS
     ******************************************************************************/↵↵
    0.07
    hall
    0.07
     substances
    0.06
     jon
    0.06
    	this
    0.06
     Sergey
    0.06
     色
    0.06
    	call
    0.06
    تق
    0.06
    _ste
    0.06
    Act Density 0.029%

    No Known Activations