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

    Neuronpedia

    INDEX
    Explanations

    Late

    np_max-act · gemini-2.0-flash

    This neuron responds to the word “Late” (especially when it appears as a heading or title token).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     GOD
    -0.07
    BIN
    -0.07
     inspection
    -0.07
    egers
    -0.07
    ITTLE
    -0.07
    GetComponent
    -0.07
    _objects
    -0.07
     корп
    -0.07
     KB
    -0.06
    Выб
    -0.06
    POSITIVE LOGITS
     late
    0.16
     Late
    0.15
    Late
    0.15
    late
    0.09
    [date
    0.09
     pozdě
    0.08
    те
    0.08
     tarde
    0.08
    Lane
    0.08
    lotte
    0.08
    Act Density 0.010%

    No Known Activations