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

    Neuronpedia

    INDEX
    Explanations

    terms related to editing and translation processes

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

    translation and publication information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.54
     INTEREST
    -0.46
     interests
    -0.44
    новниш
    -0.43
     utafitiHapana
    -0.41
     rhestr
    -0.40
     interest
    -0.40
    Interests
    -0.39
    dshaw
    -0.38
     existing
    -0.38
    POSITIVE LOGITS
    tonode
    0.54
     referrerpolicy
    0.52
    Translator
    0.50
     translator
    0.48
     translators
    0.48
     translation
    0.47
     Plo
    0.46
    translator
    0.46
     Translator
    0.43
    translation
    0.41
    Act Density 0.003%

    No Known Activations