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

    Neuronpedia

    INDEX
    Explanations

    building, chasing, gauge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ག་
    0.47
     กราบ
    0.45
    ch
    0.44
     زیر
    0.44
    giphy
    0.44
     করছেন
    0.44
     ब्ल
    0.43
    chit
    0.43
    รส
    0.43
    vak
    0.42
    POSITIVE LOGITS
    ت
    0.48
     Alamos
    0.46
     inline
    0.44
     theaters
    0.44
    懟
    0.43
    predicate
    0.43
     Inline
    0.42
     ausges
    0.41
     lễ
    0.41
     qu
    0.40
    Act Density 0.003%

    No Known Activations