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

    Neuronpedia

    INDEX
    Explanations

    mentions of government or diplomatic buildings or personnel

    oai_token-act-pair · gemini-2.0-flash

    international relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     how
    -0.71
    ,
    -0.54
    пу
    -0.51
    âmica
    -0.49
     whether
    -0.49
    судар
    -0.48
     How
    -0.48
     cómo
    -0.46
     al
    -0.45
    -
    -0.44
    POSITIVE LOGITS
     Normdatei
    1.02
    GEBURTSDATUM
    1.00
    twimg
    0.98
     Efq
    0.98
    rungsseite
    0.98
     myſelf
    0.97
     EconPapers
    0.97
    wiſe
    0.96
     itſelf
    0.94
    ſelf
    0.91
    Act Density 0.976%

    No Known Activations