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

    Neuronpedia

    INDEX
    Explanations

    Hypothetical situations

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases expressing possibility or uncertainty (e.g. modal verbs like can, could, might, any, if).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .buy
    -0.07
    امل
    -0.06
     govern
    -0.06
     strawberries
    -0.06
    Reuters
    -0.06
     drown
    -0.06
    _npc
    -0.06
    živ
    -0.06
     nút
    -0.06
    區
    -0.06
    POSITIVE LOGITS
    ()]);↵
    0.07
    ifa
    0.07
     użytk
    0.07
    Evento
    0.06
     Boolean
    0.06
    ARIANT
    0.06
     sped
    0.06
     boolean
    0.06
     versa
    0.06
     particles
    0.06
    Act Density 0.028%

    No Known Activations