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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    references to historical events (mentions of battles and years/dates).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    (slot
    -0.08
     kter
    -0.07
     yards
    -0.07
     Elo
    -0.06
    	job
    -0.06
     FetchType
    -0.06
     Jade
    -0.06
     learnt
    -0.06
     sendMessage
    -0.06
    也
    -0.06
    POSITIVE LOGITS
    Launching
    0.07
    ’.↵↵
    0.06
    appe
    0.06
    onto
    0.06
     counselor
    0.06
    antiago
    0.06
    sem
    0.06
    )">
    0.06
    ULLET
    0.06
    .forEach
    0.06
    Act Density 0.007%

    No Known Activations