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

    Neuronpedia

    INDEX
    Explanations

    elements of programming or code structure

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

    adult education and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.39
     agradecimiento
    -0.38
    niosek
    -0.35
    DockStyle
    -0.34
    meiras
    -0.34
    навли
    -0.34
     decorado
    -0.33
     mensuales
    -0.33
     manuales
    -0.33
     mentira
    -0.33
    POSITIVE LOGITS
     Adult
    0.71
     GED
    0.71
    Adult
    0.70
     ESL
    0.64
     adult
    0.63
    adult
    0.59
     Outreach
    0.59
    ESL
    0.57
     tutor
    0.55
    esl
    0.53
    Act Density 0.049%

    No Known Activations