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
     Reactive
    -0.07
    -information
    -0.06
     Utt
    -0.06
    Inspector
    -0.06
     hometown
    -0.06
    Bars
    -0.06
    FINITY
    -0.06
    Compound
    -0.06
    Ask
    -0.06
    POSITIVE LOGITS
     هزینه
    0.06
    ître
    0.06
     headers
    0.06
    .sum
    0.06
    ities
    0.06
     pres
    0.06
    \Db
    0.06
     днів
    0.06
     마
    0.06
     Effective
    0.06
    Act Density 0.263%

    No Known Activations