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

    Neuronpedia

    INDEX
    Explanations

    comic books

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on mentions of "book" (and its plural "books"), marking references to books in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <N
    -0.07
    اله
    -0.06
    uto
    -0.06
    :"#
    -0.06
    nf
    -0.06
    吧
    -0.06
    ADC
    -0.06
    ″N
    -0.06
     standpoint
    -0.06
    .ManyToMany
    -0.06
    POSITIVE LOGITS
    าตร
    0.07
    -party
    0.07
    church
    0.07
    @register
    0.06
     party
    0.06
     tụ
    0.06
     therapeutic
    0.06
    quila
    0.06
     WiFi
    0.06
     incumbent
    0.06
    Act Density 0.027%

    No Known Activations