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

    Neuronpedia

    INDEX
    Explanations

    Spanish words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     respectfully
    0.66
     посу
    0.60
    𝒎
    0.57
    gameState
    0.55
    υχ
    0.55
     quoting
    0.54
    次的
    0.54
    thane
    0.53
    的一次
    0.53
    颜
    0.53
    POSITIVE LOGITS
     अनेक
    0.59
     anteriores
    0.57
    льник
    0.54
    alit
    0.54
     cuesta
    0.54
    ಗಳು
    0.54
     Thirteen
    0.52
     Redox
    0.52
     Michel
    0.52
     exodus
    0.52
    Act Density 0.001%

    No Known Activations