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

    Neuronpedia

    INDEX
    Explanations

    URLs to articles and math resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moderator
    0.38
    रानी
    0.38
    網友
    0.38
     Hadrian
    0.37
    язы
    0.36
    മാന
    0.35
    ጴ
    0.35
     eV
    0.35
    hled
    0.35
     Catarina
    0.35
    POSITIVE LOGITS
     desto
    0.39
     प्रशिक्
    0.37
     Doors
    0.37
     temu
    0.36
     食
    0.36
    Door
    0.35
    doors
    0.35
     doors
    0.35
    🗸
    0.34
     exist
    0.34
    Act Density 0.001%

    No Known Activations