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

    Neuronpedia

    INDEX
    Explanations

    town and region names

    oai_token-act-pair · gemini-2.0-flash

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [*]
    -0.62
    PhysRev
    -0.60
     EconPapers
    -0.57
    usepackage
    -0.56
     nakalista
    -0.54
     &___
    -0.53
     Vesta
    -0.53
    Hochspringen
    -0.52
    adaptiveStyles
    -0.51
    ритори
    -0.51
    POSITIVE LOGITS
    <bos>
    0.91
     للاسماء
    0.55
    ibouti
    0.53
     nahilalakip
    0.52
     byen
    0.51
     Schließlich
    0.46
    FunctionFlags
    0.45
    Története
    0.45
    Born
    0.44
    endforeach
    0.44
    Act Density 0.363%

    No Known Activations