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

    Neuronpedia

    INDEX
    Explanations

    recurring patterns or symbols in sequences of data

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

    scientific and medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mắn
    -0.65
     MainAxisSize
    -0.64
    uarine
    -0.55
     Cytometry
    -0.55
     facies
    -0.54
    uket
    -0.52
    synthesize
    -0.52
    tispiece
    -0.51
    Ӕ
    -0.50
     QUERY
    -0.50
    POSITIVE LOGITS
    ----------------
    1.49
    ---------------
    0.88
    ------------
    0.82
     -------------
    0.82
    --------------
    0.81
     ---------------
    0.79
     ------------
    0.78
     --------------
    0.77
    ------
    0.75
    -----------
    0.75
    Act Density 0.142%

    No Known Activations