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

    Neuronpedia

    INDEX
    Explanations

    text related to electrical circuits and motors

    oai_token-act-pair · gemini-2.0-flash

    electronics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ))[
    -0.57
    ={`${
    -0.55
    äiv
    -0.52
    umente
    -0.49
     onAnimation
    -0.49
    manifold
    -0.48
    ništvo
    -0.48
    antia
    -0.48
    postmedia
    -0.47
    )&&(
    -0.47
    POSITIVE LOGITS
    Electricity
    0.93
     Electricity
    0.92
     electricity
    0.89
    ValueStyle
    0.81
     ELECTRIC
    0.71
     elettrica
    0.71
     electrical
    0.70
     elektrick
    0.70
    Electrical
    0.68
    electricity
    0.68
    Act Density 0.633%

    No Known Activations