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

    Neuronpedia

    INDEX
    Explanations

    tours and visits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _handle
    -0.07
    Modules
    -0.07
     four
    -0.06
    .ne
    -0.06
    紙
    -0.06
     dance
    -0.06
     beş
    -0.06
     quoting
    -0.06
    cki
    -0.06
     USA
    -0.06
    POSITIVE LOGITS
    '''
    0.06
     fillColor
    0.06
    ophil
    0.06
    _pb
    0.06
    .ec
    0.06
    -'
    0.06
     silica
    0.06
    )!↵
    0.06
     Superintendent
    0.06
     ~/.
    0.06
    Act Density 0.064%

    No Known Activations