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

    Neuronpedia

    INDEX
    Explanations

    movie and book titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ್ರೀ
    0.38
     minify
    0.38
    )->
    0.37
     시스템
    0.36
    ্বের
    0.36
    তীশ
    0.35
     topl
    0.35
    ecimiento
    0.35
     beit
    0.35
    phrine
    0.34
    POSITIVE LOGITS
    </em>
    0.50
     trilogy
    0.46
     Alone
    0.46
     Trilogy
    0.46
     Adventures
    0.45
    spiracy
    0.45
     című
    0.44
    》（
    0.44
     Tale
    0.43
     Assass
    0.43
    Act Density 0.053%

    No Known Activations