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

    Neuronpedia

    INDEX
    Explanations

    Adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pumped
    -0.07
     zákaz
    -0.07
     concatenated
    -0.07
    .nextToken
    -0.07
    егра
    -0.07
    .ad
    -0.07
     skoro
    -0.07
    cla
    -0.07
     depleted
    -0.06
    、二
    -0.06
    POSITIVE LOGITS
     arrogant
    0.07
    .Count
    0.07
    _FILE
    0.06
     respecting
    0.06
    ☆
    0.06
     climate
    0.06
     Malays
    0.06
    ерб
    0.06
    Middleware
    0.06
    Take
    0.05
    Act Density 0.143%

    No Known Activations