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

    Neuronpedia

    INDEX
    Explanations

    Positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     legislature
    -0.07
     oe
    -0.07
     artistic
    -0.07
     emerge
    -0.06
     fueled
    -0.06
     рекоменду
    -0.06
     goodbye
    -0.06
    _Msp
    -0.06
    \xf
    -0.06
     گ
    -0.06
    POSITIVE LOGITS
     TESTING
    0.07
    Including
    0.06
     contador
    0.06
    (fileName
    0.06
    лых
    0.06
    esModule
    0.06
     almak
    0.06
    ondrous
    0.06
    ขณะ
    0.06
    //
↵
    0.06
    Act Density 0.077%

    No Known Activations