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

    Neuronpedia

    INDEX
    Explanations

    terms related to searching and using resources or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    watch movies or sites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relationship
    -0.44
    "");
    -0.40
    ANDUM
    -0.40
    <bos>
    -0.40
    ++++++++++++++++
    -0.39
     }}"></
    -0.38
     ////
    -0.38
    _;
    -0.38
    ことで
    -0.37
     basic
    -0.37
    POSITIVE LOGITS
    吃
    0.82
    Contains
    0.65
    ltä
    0.65
     dùng
    0.64
     zákaz
    0.59
     吃
    0.57
    colors
    0.56
    Hein
    0.56
     kijk
    0.56
    inspir
    0.55
    Act Density 0.003%

    No Known Activations