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

    Neuronpedia

    INDEX
    Explanations

    occurrences of surprising or unexpected events and outcomes in competitive contexts

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

    unexpected outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roda
    -0.44
     slaves
    -0.42
     WHE
    -0.40
    Slave
    -0.38
    Rein
    -0.37
    Boot
    -0.37
     water
    -0.37
     Cumming
    -0.36
     manne
    -0.36
    Shiro
    -0.36
    POSITIVE LOGITS
     underdog
    0.61
     Überras
    0.60
    IsMutable
    0.58
     überras
    0.58
    StructEnd
    0.57
    featureID
    0.55
     surpresa
    0.54
     unexpectedly
    0.54
    richTextPanel
    0.54
    تقاوى
    0.52
    Act Density 0.012%

    No Known Activations