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

    Neuronpedia

    INDEX
    Explanations

    words related to scientific experiments and measurement

    oai_token-act-pair · gemini-2.0-flash

    width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     antichi
    -0.63
     africain
    -0.56
     antigos
    -0.51
     spears
    -0.50
    neth
    -0.49
     reflecting
    -0.49
     naturels
    -0.49
     africains
    -0.48
     digne
    -0.48
     dites
    -0.48
    POSITIVE LOGITS
     виправивши
    0.83
     Vikipedi
    0.79
     tartalomajánló
    0.77
    ImageContext
    0.76
    InjectAttribute
    0.72
    RunWith
    0.71
    tovers
    0.68
     useContext
    0.65
    AndEndTag
    0.65
    يكب
    0.64
    Act Density 3.912%

    No Known Activations