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

    Neuronpedia

    INDEX
    Explanations

    the word "key" plus words near it that could be important

    oai_token-act-pair · gemini-2.0-flash

    key concepts or factors

    np_token-act-pair-logits · gpt-4o-mini

    key

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.79
     <=",
    -0.72
     CURIAM
    -0.69
     vital
    -0.67
     crucial
    -0.63
     saites
    -0.63
     importante
    -0.62
     major
    -0.61
    ChildScrollView
    -0.61
     important
    -0.60
    POSITIVE LOGITS
     steps
    0.64
     pleaſure
    0.59
     Steps
    0.57
     pieces
    0.54
     component
    0.53
    닌
    0.52
     terms
    0.52
     components
    0.52
     paragraphs
    0.51
    COMPONENT
    0.51
    Act Density 1.349%

    No Known Activations