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

    Neuronpedia

    INDEX
    Explanations

    language related to transformation and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    transform, transformation, transforming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     流行
    -0.39
    catcher
    -0.39
    MemoryWarning
    -0.38
    Bronnen
    -0.37
     ComVisible
    -0.37
     stieg
    -0.36
    Rode
    -0.36
     jää
    -0.35
     figure
    -0.35
    serviceWorker
    -0.34
    POSITIVE LOGITS
     transformation
    0.73
     Transformation
    0.71
     Transform
    0.67
     transform
    0.67
     makeover
    0.66
     transforma
    0.65
     transforming
    0.64
    Transformation
    0.63
    transformation
    0.63
     transformations
    0.61
    Act Density 0.060%

    No Known Activations