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

    Neuronpedia

    INDEX
    Explanations

    view page source or details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Feria
    0.43
    actic
    0.39
    icill
    0.39
     podía
    0.39
    emis
    0.39
    mild
    0.39
     pudieran
    0.39
     podían
    0.38
     habla
    0.38
    zina
    0.38
    POSITIVE LOGITS
    erView
    0.40
     view
    0.40
    View
    0.39
     summary
    0.39
    ListView
    0.39
     >>>
    0.38
    ক্
    0.38
    …
    0.38
    ↗
    0.38
    浒
    0.38
    Act Density 0.001%

    No Known Activations