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

    Neuronpedia

    INDEX
    Explanations

    references to physical violence and injury

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

    body parts following pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     design
    -0.43
     stake
    -0.40
     robus
    -0.39
     descriptions
    -0.39
     expertise
    -0.36
    uxxxx
    -0.35
    TextAppearance
    -0.35
     robustness
    -0.34
     decisions
    -0.33
     description
    -0.33
    POSITIVE LOGITS
    enterOuterAlt
    0.58
    writeFieldEnd
    0.57
     SQLAlchemy
    0.54
    Välislingid
    0.53
    GTCX
    0.52
    ]")]
    0.51
     CallOverrides
    0.50
    antMatchers
    0.47
     gynhyrchwyd
    0.47
     defaultstate
    0.46
    Act Density 0.029%

    No Known Activations