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

    Neuronpedia

    INDEX
    Explanations

    warnings and safety instructions related to medication usage

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

    drink test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.77
    medriver
    -0.72
    migrationBuilder
    -0.71
    RegressionTest
    -0.69
    -0.69
    matchCondition
    -0.66
     ffilmiau
    -0.66
     surla
    -0.66
     ujednoznacz
    -0.65
     שוליים
    -0.65
    POSITIVE LOGITS
     råd
    0.40
     darse
    0.36
     Decke
    0.36
     boire
    0.35
     bescher
    0.34
     Dedicated
    0.34
     nécessite
    0.34
     proteger
    0.34
     disminuir
    0.34
     épaules
    0.34
    Act Density 0.001%

    No Known Activations