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

    Neuronpedia

    INDEX
    Explanations

    state and specific following noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zaj
    0.41
     airspace
    0.40
     cognition
    0.40
     लगाएंगे
    0.40
     लेंगे
    0.39
     जाएंगी
    0.39
     village
    0.39
    кли
    0.38
     Engage
    0.38
     TG
    0.38
    POSITIVE LOGITS
    luor
    0.44
    Jour
    0.43
    aria
    0.42
    ino
    0.42
    fin
    0.42
    ret
    0.41
    ép
    0.41
    rib
    0.40
    stap
    0.40
    aha
    0.39
    Act Density 0.000%

    No Known Activations