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

    Neuronpedia

    INDEX
    Explanations

    role introduction or AI identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هنا
    0.40
    FEM
    0.39
    فري
    0.38
    ẖ
    0.38
     varied
    0.37
    ႉ
    0.36
     CRC
    0.35
     variado
    0.35
     NKG
    0.35
     Here
    0.35
    POSITIVE LOGITS
    我会
    0.48
    hello
    0.45
    我已经
    0.43
     hello
    0.41
     நான்
    0.41
    我很
    0.40
    resolve
    0.40
     دارم
    0.39
    ato
    0.39
    我是
    0.38
    Act Density 0.006%

    No Known Activations