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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron activates on the appearance of the answer option “Yes” in the Q&A prompt.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ใ
    -0.06
    éc
    -0.06
     bà
    -0.06
     mb
    -0.06
    ’m
    -0.06
    IAM
    -0.06
    _instruction
    -0.06
    iphery
    -0.06
     BR
    -0.06
     Bà
    -0.06
    POSITIVE LOGITS
     Guitar
    0.07
    мп
    0.07
    .Assert
    0.06
    DWORD
    0.06
    ebi
    0.06
     pitcher
    0.06
     HOLDER
    0.06
    公路
    0.06
     tags
    0.06
    usz
    0.06
    Act Density 0.002%

    No Known Activations