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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “first time” (or similar phrasing) that signal a repeated or prior occurrence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nostra
    -0.07
     sanctuary
    -0.07
    excluding
    -0.07
    혹
    -0.07
    _DAY
    -0.06
    rador
    -0.06
     Saga
    -0.06
    논
    -0.06
    NAS
    -0.06
    236
    -0.06
    POSITIVE LOGITS
     openid
    0.06
     multit
    0.06
    (=)
    0.06
    							↵
    0.06
    _almost
    0.06
    weit
    0.06
     concentrates
    0.06
    )":
    0.06
     Stap
    0.06
     correlated
    0.06
    Act Density 0.009%

    No Known Activations