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

    Neuronpedia

    INDEX
    Explanations

    -ic/-onic/-anic endings

    np_max-act · gemini-2.0-flash

    The neuron flags fragments of chemical compound names—especially common organic nomenclature suffixes like “-onic,” “-anic,” and “-otic.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     denně
    -0.07
    11
    -0.07
     WILL
    -0.07
    delay
    -0.07
     rotterdam
    -0.07
    60
    -0.06
    877
    -0.06
    10
    -0.06
    (L
    -0.06
    81
    -0.06
    POSITIVE LOGITS
    ic
    0.16
    mic
    0.14
    IC
    0.13
    onic
    0.12
    ovic
    0.12
    etic
    0.12
    otic
    0.11
    elic
    0.11
    vic
    0.11
    olic
    0.11
    Act Density 0.213%

    No Known Activations