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

    Neuronpedia

    INDEX
    Explanations

    location names like cities and towns

    oai_token-act-pair · gemini-2.0-flash

    place names and locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <eos>
    -0.50
    Read
    -0.49
     and
    -0.49
     time
    -0.47
     (
    -0.47
    ,
    -0.46
    esm
    -0.44
     I
    -0.42
     [
    -0.42
    (
    -0.41
    POSITIVE LOGITS
     nahilalakip
    1.40
    GEBURTSDATUM
    1.34
     виправивши
    1.22
    NameInMap
    1.20
     kasarigan
    1.16
     ***!
    1.14
    WithIOException
    1.09
    expandindo
    1.07
    Autoritní
    1.05
    SourceChecksum
    1.05
    Act Density 1.455%

    No Known Activations