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

    Neuronpedia

    INDEX
    Explanations

    occurrences of underscores in the text

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

    user ID or account identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.47
    troppo
    -0.46
    +:+
    -0.45
    hept
    -0.40
    EndContext
    -0.40
    matchCondition
    -0.39
    mente
    -0.39
    theless
    -0.38
    else
    -0.38
    then
    -0.38
    POSITIVE LOGITS
     ID
    0.73
    idUser
    0.69
    setId
    0.69
     IDs
    0.67
     identification
    0.66
    getId
    0.64
     المعيارى
    0.64
     setId
    0.63
    ID
    0.62
     ids
    0.61
    Act Density 0.005%

    No Known Activations