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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ');?></
    -0.07
     Elm
    -0.07
    ibly
    -0.07
    .peer
    -0.07
    (light
    -0.06
     oval
    -0.06
    carousel
    -0.06
     chair
    -0.06
    torch
    -0.06
    record
    -0.06
    POSITIVE LOGITS
    的声音
    0.07
    �
    0.07
     owned
    0.06
     Tmax
    0.06
    ині
    0.06
    Converter
    0.06
    atonin
    0.06
    lerinin
    0.06
     stacked
    0.06
     unrecognized
    0.06
    Act Density 0.010%

    No Known Activations