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

    Neuronpedia

    INDEX
    Explanations

    the letter "w", especially lowercase

    oai_token-act-pair · gemini-2.0-flash

    w

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    was
    -0.61
    ie
    -0.57
    ю
    -0.56
    ere
    -0.56
    not
    -0.52
    u
    -0.52
    wee
    -0.52
     Regie
    -0.50
    um
    -0.50
    we
    -0.50
    POSITIVE LOGITS
    makeText
    0.98
    Rüyada
    0.95
    ILayout
    0.91
    bootstrapcdn
    0.90
     يتيمه
    0.89
    :+:
    0.88
    createStatement
    0.84
    wieś
    0.84
    complexContent
    0.84
     &___
    0.84
    Act Density 0.759%

    No Known Activations