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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     свя
    -0.08
     conglomer
    -0.08
     accidentally
    -0.08
     nearly
    -0.07
    744
    -0.07
     milioane
    -0.07
     etree
    -0.07
     frustrated
    -0.07
    136
    -0.07
     millón
    -0.07
    POSITIVE LOGITS
     기간
    0.14
    期間
    0.13
    期间
    0.12
    Duration
    0.11
     období
    0.11
     periods
    0.11
     течение
    0.11
     periode
    0.11
    _duration
    0.10
    Periods
    0.10
    Act Density 0.050%

    No Known Activations