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

    Neuronpedia

    INDEX
    Explanations

    interacting with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     using
    1.37
     bằng
    1.24
     menggunakan
    1.16
     by
    1.14
     usando
    1.13
     USING
    1.13
     utilizing
    1.13
     involving
    1.12
    ด้วย
    1.12
     Using
    1.11
    POSITIVE LOGITS
     সৌন্দর্য
    0.66
    能够
    0.61
    \":\"
    0.59
     कक्ष
    0.59
    reason
    0.59
    tolist
    0.57
     ____
    0.55
    کھ
    0.55
    ത്തേ
    0.55
    危害
    0.55
    Act Density 0.214%

    No Known Activations