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

    Neuronpedia

    INDEX
    Explanations

    references to numerical or statistical data

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

    U.S. Air Force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.52
     AssemblyCulture
    -0.52
    elemField
    -0.50
     <>",
    -0.48
    новниш
    -0.47
     Thü
    -0.47
    -------------</
    -0.47
    parsedMessage
    -0.46
    oredCriteria
    -0.46
     Administrativna
    -0.45
    POSITIVE LOGITS
     auroit
    0.54
     feroit
    0.50
     hobbies
    0.47
     étoit
    0.42
     <<<<<<<<<<<<<<
    0.41
     avoient
    0.40
    ftagPool
    0.39
     mourners
    0.38
    +:+
    0.36
     keluarga
    0.36
    Act Density 0.001%

    No Known Activations