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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash

    This neuron activates on LaTeX macro tokens (e.g. command names like “\frac”, “\partial”, “\overset”, “\textbf”, etc.) within math expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .photo
    -0.07
     ecstasy
    -0.06
    WebService
    -0.06
    -image
    -0.06
    .setUser
    -0.06
    (',')
    -0.06
    Them
    -0.06
     Playoff
    -0.06
     shots
    -0.06
     zim
    -0.06
    POSITIVE LOGITS
    шла
    0.06
    워크
    0.06
     діяльність
    0.06
     دستور
    0.06
     کوه
    0.06
    POINT
    0.06
    :{
↵
    0.06
     confines
    0.06
    -click
    0.06
     인터넷
    0.06
    Act Density 0.022%

    No Known Activations