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

    Neuronpedia

    INDEX
    Explanations

    Scientific/biological texts

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific chemical compound names or formula abbreviations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    857
    -0.06
    biên
    -0.06
     поз
    -0.06
    ?>"></
    -0.06
    agram
    -0.06
    anan
    -0.05
     patched
    -0.05
    only
    -0.05
     edilen
    -0.05
     的
    -0.05
    POSITIVE LOGITS
     دستور
    0.08
     बह
    0.08
     особ
    0.07
    :');↵
    0.07
     ret
    0.06
     	↵
    0.06
    gtk
    0.06
     yp
    0.06
     겁
    0.06
    仿
    0.06
    Act Density 0.056%

    No Known Activations