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

    Neuronpedia

    INDEX
    Explanations

    ratios and proportions

    np_max-act · gemini-2.0-flash

    The neuron responds to technical biochemical compound names, especially hormone or enzyme names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     border
    -0.07
    或
    -0.07
     containing
    -0.06
    ![
    -0.06
    引
    -0.06
     altern
    -0.06
     independence
    -0.06
     apart
    -0.06
    .dir
    -0.06
    shirt
    -0.06
    POSITIVE LOGITS
    _sold
    0.07
     ranch
    0.06
     Albuquerque
    0.06
     hashlib
    0.06
     Wass
    0.06
     Listed
    0.06
     NX
    0.06
     Franti
    0.06
     příležit
    0.06
     Hind
    0.06
    Act Density 0.011%

    No Known Activations