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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens forming systematic chemical names—particularly ones starting with “2-Chloro-” (i.e. chlorinated heterocyclic compound names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     baj
    -0.06
    _depend
    -0.06
     Möglichkeit
    -0.06
    妻
    -0.06
     resignation
    -0.06
    _PUSHDATA
    -0.06
     виник
    -0.05
    .bel
    -0.05
    .ed
    -0.05
    频次
    -0.05
    POSITIVE LOGITS
    oro
    0.08
    olo
    0.07
     Campo
    0.07
    .dateTime
    0.07
    ριος
    0.07
     trade
    0.07
    asto
    0.07
    store
    0.07
    ro
    0.07
    o
    0.07
    Act Density 0.006%

    No Known Activations