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

    Neuronpedia

    INDEX
    Explanations

    closing brace or tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     epidemics
    0.29
     voices
    0.28
     extrac
    0.28
     newsletters
    0.27
     voyages
    0.27
     acquisitions
    0.27
     verdicts
    0.27
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.26
     registries
    0.26
     outputs
    0.26
    POSITIVE LOGITS
    www
    0.27
    रा
    0.27
    ϛ
    0.27
    OW
    0.26
    used
    0.26
    しっかりと
    0.25
    ז
    0.25
    RAM
    0.25
    的首
    0.25
    smtb
    0.25
    Act Density 0.080%

    No Known Activations