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

    Neuronpedia

    INDEX
    Explanations

    limitations and considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ලය
    0.61
     demais
    0.60
    দেশ
    0.58
     dom
    0.57
    คือ
    0.56
     คือ
    0.56
     అయినా
    0.55
    خان
    0.55
     anyways
    0.55
     hẹn
    0.54
    POSITIVE LOGITS
    )..
    1.32
    ..(
    1.24
    ..
    1.22
    .)..
    1.16
    ..)
    1.07
    although
    1.06
    .."
    1.05
    .).
    1.01
    যদিও
    0.98
     although
    0.96
    Act Density 0.241%

    No Known Activations