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

    Neuronpedia

    INDEX
    Explanations

    cheese

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “cheese” (in particular the “ese” suffix), effectively spotting when the text mentions cheese.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     タ
    -0.07
    _allocator
    -0.07
     manifested
    -0.07
    outline
    -0.07
    ategor
    -0.06
    Sector
    -0.06
    (rect
    -0.06
    cks
    -0.06
     Fight
    -0.06
     Muk
    -0.06
    POSITIVE LOGITS
     cheese
    0.12
     Cheese
    0.10
     cheeses
    0.10
     chees
    0.08
     ÜNİVERSİTESİ
    0.08
     verde
    0.07
    rese
    0.07
     cheesy
    0.07
    最高
    0.07
     standardUserDefaults
    0.07
    Act Density 0.004%

    No Known Activations