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

    Neuronpedia

    INDEX
    Explanations

    references to physical injuries or damage

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

    broken or not working

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uLocal
    -0.53
     חיצוניים
    -0.52
     Latitude
    -0.50
    SerializeField
    -0.49
    ImageField
    -0.49
     Regard
    -0.46
     Dhabi
    -0.45
    談社
    -0.45
    adaptiveStyles
    -0.44
     Tara
    -0.43
    POSITIVE LOGITS
     break
    1.08
    break
    1.04
     broken
    1.03
     BREAK
    1.01
     Break
    0.98
     breaking
    0.98
    Break
    0.98
     Broken
    0.96
     broke
    0.96
    Broken
    0.95
    Act Density 0.017%

    No Known Activations