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

    Neuronpedia

    INDEX
    Explanations

    chemical formulas and equations

    oai_token-act-pair · gemini-2.0-flash

    xe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.63
     neuve
    -0.53
    zelf
    -0.52
    stätten
    -0.51
     purpoſe
    -0.50
     ſame
    -0.49
     PSN
    -0.48
     Consumo
    -0.48
     seyn
    -0.48
    IFICATIONS
    -0.48
    POSITIVE LOGITS
    <bos>
    1.50
    httphttps
    0.82
    ंदीखरीदारी
    0.81
     المعيارى
    0.72
     intptr
    0.67
    '>
    0.66
    '>"
    0.65
    ">)</
    0.65
    '))
    0.64
    __":
    0.64
    Act Density 22.881%

    No Known Activations