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

    Neuronpedia

    INDEX
    Explanations

    US Constitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    А
    0.53
    ),
    0.51
     poświę
    0.50
    },
    0.50
    lina
    0.49
    ]।
    0.49
     Kharkiv
    0.48
    "。
    0.47
    ৤
    0.47
    ।*
    0.46
    POSITIVE LOGITS
    ார
    0.70
    ות
    0.63
    א
    0.62
    ва
    0.59
    ת
    0.56
    та
    0.56
    л
    0.55
    ود
    0.55
    त
    0.53
    ્
    0.52
    Act Density 0.002%

    No Known Activations