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

    Neuronpedia

    INDEX
    Explanations

    concepts related to scientific research and findings

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

    academic research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.77
    ConstraintMaker
    -0.64
     $_(
    -0.62
     $_"
    -0.59
    ſammen
    -0.58
     queſta
    -0.58
    ſicht
    -0.56
    parsedMessage
    -0.56
     kaarangay
    -0.56
    ſelves
    -0.56
    POSITIVE LOGITS
     Wohl
    0.35
    ว์
    0.35
     i
    0.34
    quel
    0.33
     with
    0.33
     for
    0.32
     (
    0.32
     reflexionar
    0.31
     on
    0.31
     unui
    0.31
    Act Density 0.155%

    No Known Activations