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

    Neuronpedia

    INDEX
    Explanations

    concept or idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ్రు
    0.94
     Ordered
    0.89
    দে
    0.88
     effectués
    0.82
     역할을
    0.82
    を指定
    0.80
     قانونی
    0.80
     режими
    0.79
     Determined
    0.79
     결과
    0.77
    POSITIVE LOGITS
     notions
    1.64
     ideas
    1.60
     concepts
    1.59
     ideias
    1.51
     notion
    1.49
     idea
    1.46
     concept
    1.44
     conceptos
    1.37
    concept
    1.33
    ideas
    1.32
    Act Density 0.228%

    No Known Activations