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

    Neuronpedia

    INDEX
    Explanations

    AI Chatbot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     un
    0.76
     received
    0.73
     skept
    0.73
     cel
    0.66
     automatic
    0.66
     pass
    0.66
     recipients
    0.65
     daily
    0.65
     formal
    0.64
     stands
    0.64
    POSITIVE LOGITS
    Palindrome
    0.88
     Collage
    0.84
    嘊
    0.80
    hevik
    0.79
     Taxonomy
    0.76
    仕様
    0.76
    Anagram
    0.75
    Genus
    0.75
     Ballet
    0.75
     Tetrahedron
    0.74
    Act Density 0.029%

    No Known Activations