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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ol
    -0.07
    classification
    -0.07
    uddle
    -0.07
    .img
    -0.07
    灰
    -0.07
    ]=="
    -0.06
     berth
    -0.06
    -API
    -0.06
    .marker
    -0.06
     cil
    -0.06
    POSITIVE LOGITS
    	private
    0.07
    _and
    0.07
    其中
    0.07
     NSNumber
    0.07
     شهری
    0.06
     birden
    0.06
     and
    0.06
    =db
    0.06
    .GET
    0.06
     špat
    0.06
    Act Density 0.058%

    No Known Activations