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

    Neuronpedia

    INDEX
    Explanations

    Bullet points

    np_max-act · gemini-2.0-flash

    This neuron detects the instruction phrase “bullet point” (i.e. formatting directions for bullet points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    006
    -0.07
    areth
    -0.07
    网址
    -0.07
    歌
    -0.07
    IVATE
    -0.06
     Jerusalem
    -0.06
    oor
    -0.06
     temperatura
    -0.06
    opers
    -0.06
    َر
    -0.06
    POSITIVE LOGITS
     bullet
    0.08
     Bullet
    0.07
     grub
    0.07
     Arrow
    0.06
    ULATOR
    0.06
     пунк
    0.06
    เซ
    0.06
     sess
    0.06
    吉
    0.06
     jwt
    0.06
    Act Density 0.003%

    No Known Activations