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

    Neuronpedia

    INDEX
    Explanations

    expressions of quality or evaluation related to experiences

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

    Intensifiers like "very", "really", or punctuation

    np_acts-logits-general · gemini-2.0-flash

    degree and intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.58
    MENAFN
    -0.58
    queryInterface
    -0.56
     GenerationType
    -0.54
     onAnimation
    -0.52
    oneofs
    -0.51
     hini
    -0.49
    TagHelpers
    -0.49
     noqa
    -0.47
    Autoritní
    -0.47
    POSITIVE LOGITS
     very
    1.72
     VERY
    1.56
     Very
    1.53
    Very
    1.51
    VERY
    1.48
    very
    1.45
     extremely
    1.43
     REALLY
    1.28
     really
    1.27
    extremely
    1.25
    Act Density 0.212%

    No Known Activations