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

    Neuronpedia

    INDEX
    Explanations

    location names, especially cities and districts

    oai_token-act-pair · gemini-2.0-flash

    Locations and administrative divisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.72
    Попис
    -0.49
    SPJ
    -0.48
    enumii
    -0.44
     méxico
    -0.44
    SuppressLint
    -0.42
    NSW
    -0.41
    Israël
    -0.41
     italiane
    -0.40
    ginfo
    -0.40
    POSITIVE LOGITS
     countries
    0.75
    Nazionale
    0.74
     internasional
    0.69
    Countries
    0.66
     lenker
    0.66
     international
    0.66
     diplomatic
    0.66
    تقاوى
    0.65
     internacional
    0.64
    KURZBESCHREIBUNG
    0.64
    Act Density 14.077%

    No Known Activations