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

    Neuronpedia

    INDEX
    Explanations

    multiple choice questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     фанта
    -0.09
     uname
    -0.07
    Dims
    -0.07
    imt
    -0.07
     Applications
    -0.07
     meters
    -0.07
    .gz
    -0.07
     Transformation
    -0.07
     primit
    -0.07
    Reconnect
    -0.07
    POSITIVE LOGITS
     simultaneous
    0.09
    Ranking
    0.09
     ranking
    0.09
     singled
    0.09
     einzelne
    0.09
     Checkbox
    0.09
     exclusive
    0.09
    选四
    0.09
     winner
    0.08
     Ranking
    0.08
    Act Density 0.027%

    No Known Activations