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

    Neuronpedia

    INDEX
    Explanations

    geography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    木坂
    -2.20
    ];
    -2.13
    𖧵
    -2.11
    孭
    -2.00
    蓠
    -1.91
    怱
    -1.91
    颪
    -1.91
    のお知らせ
    -1.90
    𖣘
    -1.87
    齶
    -1.86
    POSITIVE LOGITS
    f
    2.44
    e
    2.27
    3
    2.23
    .
    2.20
    b
    2.09
    0
    2.00
    ve
    1.95
    </h4>
    1.89
    c
    1.83
     estekak
    1.80
    Act Density 0.012%

    No Known Activations