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

    Neuronpedia

    INDEX
    Explanations

    measurement units or things that can be counted

    oai_token-act-pair · gemini-2.0-flash

    measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     colourless
    -0.65
     ơn
    -0.63
    eachtet
    -0.61
    tamol
    -0.60
     BnF
    -0.60
     xlink
    -0.59
     Berries
    -0.59
     financière
    -0.58
    bkz
    -0.57
    etano
    -0.57
    POSITIVE LOGITS
    <bos>
    0.69
    '
    0.64
     
    0.57
     The
    0.53
     members
    0.51
    ’
    0.50
    The
    0.50
    ʻ
    0.50
     <=",
    0.49
    BeginContext
    0.48
    Act Density 2.506%

    No Known Activations