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

    Neuronpedia

    INDEX
    Explanations

    source code / technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цездатний
    -0.64
    oredCriteria
    -0.62
    Disliked
    -0.60
     becauſe
    -0.59
    WebVitals
    -0.58
    LookAnd
    -0.57
     these
    -0.57
    龇
    -0.56
     theſe
    -0.56
     depends
    -0.56
    POSITIVE LOGITS
    //
    0.55
    <bos>
    0.52
    /
    0.51
     or
    0.50
     muun
    0.48
    外部リンク
    0.44
    のだろうか
    0.44
     /
    0.43
    <tbody>
    0.43
     např
    0.42
    Act Density 0.002%

    No Known Activations