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

    Neuronpedia

    INDEX
    Explanations

    the mention of Polish villages, counties, or regions

    oai_token-act-pair · gemini-2.0-flash

    Place names and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InitVars
    -0.98
    Personensuche
    -0.96
    TagMode
    -0.94
    IntoConstraints
    -0.91
    UnusedPrivate
    -0.85
    脚注の使い方
    -0.80
     nakalista
    -0.74
     HasFactory
    -0.70
     kasarigan
    -0.69
    ьаж
    -0.68
    POSITIVE LOGITS
    QUID
    0.44
     trí
    0.43
     onItemClick
    0.39
    pan
    0.37
     musia
    0.37
     er
    0.37
     pan
    0.37
    LEV
    0.36
    cô
    0.36
    ecc
    0.36
    Act Density 0.277%

    No Known Activations