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

    Neuronpedia

    INDEX
    Explanations

    terms related to observation and discrimination in scientific research

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

    observational, discriminative, associativity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alpina
    -0.54
    a
    -0.52
    Rectangle
    -0.52
     rectangle
    -0.51
    e
    -0.51
    プーン
    -0.50
    FieldType
    -0.49
    ConnectionState
    -0.48
     Rinehart
    -0.47
    LineWidth
    -0.47
    POSITIVE LOGITS
    ibrill
    0.67
    Celebr
    0.67
     않
    0.63
    ArgumentParser
    0.60
    0.59
     Celebr
    0.59
     Illumin
    0.58
    cuador
    0.58
     illumin
    0.56
     celebr
    0.56
    Act Density 0.093%

    No Known Activations