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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the possessive pronoun “its” immediately followed by the word “contributors” (as in license/disclaimer notices).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	im
    -0.07
    +B
    -0.07
     Trends
    -0.06
    +p
    -0.06
    ector
    -0.06
    .Mutable
    -0.06
     Preis
    -0.06
    .days
    -0.06
    >_
    -0.06
    .www
    -0.06
    POSITIVE LOGITS
    취
    0.07
     đặc
    0.07
     güç
    0.07
    št
    0.06
    sk
    0.06
     lax
    0.06
     tink
    0.06
     Bot
    0.06
    obl
    0.06
     exce
    0.06
    Act Density 0.002%

    No Known Activations