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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and legal disclaimers

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

    Followed by "WITHOUT" or "LOW"

    np_acts-logits-general · gemini-2.0-flash

    LOW HIGH

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.72
    닙
    -0.59
     selatan
    -0.54
    encodeWith
    -0.53
    IsContent
    -0.52
    iske
    -0.51
     AssemblyCulture
    -0.51
    AndEndTag
    -0.51
     off
    -0.51
    FormTagHelper
    -0.51
    POSITIVE LOGITS
     VERY
    0.59
     TWICE
    0.54
     REALLY
    0.53
    ])):
    0.50
     LEAST
    0.50
     MUCH
    0.49
     }</
    0.49
     MANY
    0.49
    muer
    0.47
     NOTHING
    0.47
    Act Density 0.220%

    No Known Activations