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

    Neuronpedia

    INDEX
    Explanations

    high-impact or dramatic actions, events, and expressions

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

    ending in "ed" or similar suffixes

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    volving
    -0.59
    ising
    -0.59
    izable
    -0.58
    IZING
    -0.58
    izing
    -0.57
    Приятного
    -0.57
    CppCodeGen
    -0.57
    TypedDataSet
    -0.57
     CURIAM
    -0.57
    iser
    -0.56
    POSITIVE LOGITS
    ed
    1.11
     ed
    0.77
    ED
    0.74
    eed
    0.72
    Ed
    0.67
     ED
    0.58
    hed
    0.58
    jed
    0.57
    éd
    0.55
    edd
    0.55
    Act Density 0.167%

    No Known Activations