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

    Neuronpedia

    INDEX
    Explanations

    DDR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    城乡
    -0.09
     내
    -0.08
     tratando
    -0.08
     помещ
    -0.08
     tratar
    -0.07
    ствами
    -0.07
     уволь
    -0.07
    cements
    -0.07
     ου
    -0.07
     vacant
    -0.07
    POSITIVE LOGITS
     tyres
    0.09
     flores
    0.08
     korral
    0.08
    高速
    0.08
     moderated
    0.08
     Operation
    0.08
     mobilisation
    0.08
     Frequency
    0.08
     Ops
    0.08
     Ericsson
    0.08
    Act Density 0.002%

    No Known Activations