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

    Neuronpedia

    INDEX
    Explanations

    http get routes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moelle
    0.43
    兕
    0.40
    rictor
    0.40
    molecular
    0.39
    ্লোক
    0.39
    нити
    0.39
    Occup
    0.38
    avaient
    0.38
     preservar
    0.37
    뺀
    0.37
    POSITIVE LOGITS
    /
    0.60
     '/
    0.53
     `/
    0.44
    /{
    0.43
    ('/
    0.43
    /(
    0.43
    }/
    0.42
     $/
    0.42
     /
    0.42
    ("/
    0.41
    Act Density 0.008%

    No Known Activations