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

    Neuronpedia

    INDEX
    Explanations

    the word "screen" and the word "point"

    oai_token-act-pair · gemini-2.0-flash

    screen point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anſ
    -1.55
     Monfieur
    -1.48
     Reſ
    -1.45
     Efq
    -1.41
     ―――――
    -1.40
     Diſ
    -1.38
     myſelf
    -1.38
     Houſe
    -1.34
     Theſe
    -1.34
     Jefus
    -1.32
    POSITIVE LOGITS
    <bos>
    0.74
     D
    0.68
     S
    0.67
     
    0.66
     R
    0.65
     L
    0.65
    .
    0.65
     her
    0.64
     his
    0.63
     T
    0.63
    Act Density 0.480%

    No Known Activations