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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash

    The neuron fires on descriptive adjectives and noun fragments that specify an animal’s physical characteristics (size, body parts, colors, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hydro
    -0.07
     fiber
    -0.07
    MMMM
    -0.07
     THC
    -0.07
     tanker
    -0.07
    紅
    -0.07
    _dim
    -0.07
    TEGR
    -0.07
    COL
    -0.06
    CONS
    -0.06
    POSITIVE LOGITS
    PagerAdapter
    0.06
     assortment
    0.06
    ifikasi
    0.06
     svenska
    0.06
     adalah
    0.06
    jmp
    0.06
     Đây
    0.06
     questa
    0.06
     عقد
    0.06
    ascade
    0.06
    Act Density 0.402%

    No Known Activations