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

    Neuronpedia

    INDEX
    Explanations

    objectives and aims of various studies

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

    study purpose or objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.65
    MLLoader
    -0.63
     tartalomajánló
    -0.57
    المصادر
    -0.54
     Normdatei
    -0.54
    reportWebVitals
    -0.54
    følgelig
    -0.52
    principalColumn
    -0.50
     feroit
    -0.50
     queſta
    -0.50
    POSITIVE LOGITS
    OrBuilder
    0.36
     par
    0.31
     objective
    0.31
     purpose
    0.29
    
    0.28
     expression
    0.28
    saraba
    0.28
    purpose
    0.27
     limit
    0.27
     representation
    0.27
    Act Density 0.300%

    No Known Activations