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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bylo
    -0.07
    uario
    -0.06
    جموع
    -0.06
     umož
    -0.06
     зв
    -0.06
     Ra
    -0.06
    (writer
    -0.06
     yerini
    -0.06
     racial
    -0.05
     включ
    -0.05
    POSITIVE LOGITS
    lland
    0.07
    Fatal
    0.07
     scaleY
    0.07
     Huge
    0.06
    ancia
    0.06
     cooker
    0.06
     cheerful
    0.06
     єв
    0.06
     strokeLine
    0.06
    ificent
    0.06
    Act Density 0.002%

    No Known Activations