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

    Neuronpedia

    INDEX
    Explanations

    hyphens and zeros

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Santa
    -0.07
     salt
    -0.07
     algae
    -0.06
    rica
    -0.06
     Transformer
    -0.06
    Santa
    -0.06
     Кур
    -0.06
    _ar
    -0.06
     buses
    -0.06
     nc
    -0.06
    POSITIVE LOGITS
     loạt
    0.07
     những
    0.07
    Rest
    0.07
    .decrypt
    0.07
    (bodyParser
    0.06
     Summary
    0.06
    則
    0.06
    .getOrElse
    0.06
     sensational
    0.06
    ださい
    0.06
    Act Density 0.003%

    No Known Activations