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

    Neuronpedia

    INDEX
    Explanations

    M

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Truthy
    0.37
     অনুবাদ
    0.36
     Isid
    0.36
     isomerization
    0.36
    iativa
    0.36
    ্যন্ত
    0.35
    िएंट
    0.35
    ໃຫ້
    0.35
     isomorphisms
    0.35
    uestas
    0.35
    POSITIVE LOGITS
    絫
    0.42
     রিপ
    0.41
    diyl
    0.40
     busy
    0.39
    acchi
    0.38
    OR
    0.38
     hac
    0.38
    odu
    0.37
     δικ
    0.37
     plotted
    0.37
    Act Density 0.000%

    No Known Activations