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

    Neuronpedia

    INDEX
    Explanations

    concepts and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dijeron
    0.45
     pierwsze
    0.45
     Eğer
    0.45
     cosas
    0.44
    это
    0.44
     bilmi
    0.44
     ONLY
    0.43
     actually
    0.42
     decirle
    0.42
     ahorita
    0.41
    POSITIVE LOGITS
     באמצעות
    0.34
    liche
    0.33
    ifting
    0.33
    volving
    0.33
    TAIN
    0.33
     stets
    0.33
    を通じて
    0.33
    orphic
    0.32
     महत्वपूर्ण
    0.31
    涵盖
    0.30
    Act Density 0.162%

    No Known Activations