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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the phrase “it’s good.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     capsule
    -0.06
     assez
    -0.06
    امه
    -0.06
    "}}>↵
    -0.06
     bedrooms
    -0.06
     Palo
    -0.06
    %;↵
    -0.06
     cps
    -0.06
     tespit
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Рё
    0.07
     interle
    0.06
    vé
    0.06
    ­
    0.06
    :".$
    0.06
     spep
    0.06
    將
    0.06
     Kenneth
    0.06
     облас
    0.06
     الإ
    0.06
    Act Density 0.004%

    No Known Activations