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

    Neuronpedia

    INDEX
    Explanations

    the word "transform" and its related forms

    oai_token-act-pair · gemini-2.0-flash

    transform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <h2>
    -0.86
    ↵
    -0.82
      
    -0.75
     a
    -0.75
    <h3>
    -0.71
    ↵↵
    -0.71
    ベ
    -0.68
    t
    -0.68
    <
    -0.67
     the
    -0.67
    POSITIVE LOGITS
     '\\;'
    1.27
     Efq
    1.23
     Shakspeare
    1.18
     समीक्षक
    1.17
     MainAxisSize
    1.16
    évaluateur
    1.11
     Theſe
    1.09
     myſelf
    1.09
    tvguidetime
    1.09
     avoient
    1.09
    Act Density 1.411%

    No Known Activations