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

    Neuronpedia

    INDEX
    Explanations

    the word "wash" or its variations.

    oai_token-act-pair · gemini-2.0-flash

    wash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.05
    LookAnd
    -0.91
     wash
    -0.81
    DockStyle
    -0.79
    findpost
    -0.78
    <bos>
    -0.72
     washed
    -0.71
    
    -0.71
     مرئيه
    -0.67
    httphttps
    -0.67
    POSITIVE LOGITS
     setData
    0.65
     getRequest
    0.59
    IVEREF
    0.59
    ')";
    0.59
    ukone
    0.59
     $"{
    0.58
    ิมพ์
    0.57
    ):(
    0.57
    æder
    0.56
    ensiva
    0.56
    Act Density 0.778%

    No Known Activations