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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to Markdown structural elements—especially section headers (lines beginning with one or more “#”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    νά
    -0.07
     ἐ
    -0.07
    /static
    -0.07
    erie
    -0.07
     gains
    -0.07
    をつ
    -0.07
     CROSS
    -0.06
    naz
    -0.06
     manslaughter
    -0.06
    ILES
    -0.06
    POSITIVE LOGITS
     samot
    0.07
    offee
    0.07
    erli
    0.06
     descon
    0.06
    .SizeMode
    0.06
    regn
    0.06
     اجر
    0.06
    čka
    0.06
     mnoho
    0.06
    čku
    0.06
    Act Density 0.021%

    No Known Activations