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

    Neuronpedia

    INDEX
    Explanations

    Completion or development

    np_max-act · gemini-2.0-flash

    This neuron detects nominalizations that signal outcomes or development—words like “result,” “culmination,” “growth,” or “fruition.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ещ
    -0.07
    ่าว
    -0.06
     habitual
    -0.06
     Techniques
    -0.06
    _IL
    -0.06
     sails
    -0.06
    #ac
    -0.06
    []"
    -0.06
     NBA
    -0.06
     nal
    -0.06
    POSITIVE LOGITS
    olon
    0.07
     brain
    0.07
     herb
    0.06
     thoughts
    0.06
     Roman
    0.06
     ___
    0.06
    ypo
    0.06
    (s
    0.06
     observes
    0.06
     [...]↵↵
    0.06
    Act Density 0.039%

    No Known Activations