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

    Neuronpedia

    INDEX
    Explanations

    Organization abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Capital
    -0.08
     neut
    -0.07
     берез
    -0.07
     mest
    -0.07
     рук
    -0.07
    рах
    -0.07
     overriding
    -0.06
     Saud
    -0.06
     Airlines
    -0.06
    	Dictionary
    -0.06
    POSITIVE LOGITS
    TableName
    0.07
    RAY
    0.06
    İS
    0.06
     kısm
    0.06
    [{
    0.06
    Contained
    0.06
    )size
    0.06
    uluğ
    0.06
    심
    0.06
    فاع
    0.06
    Act Density 0.032%

    No Known Activations