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

    Neuronpedia

    INDEX
    Explanations

    Hey

    np_max-act · gemini-2.0-flash

    The neuron detects the informal greeting “Hey.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Περι
    -0.06
    .encrypt
    -0.06
     diagram
    -0.06
                        ↵                    ↵
    -0.06
    iot
    -0.06
     enfer
    -0.06
    omas
    -0.06
     πάνω
    -0.05
     clouds
    -0.05
    StateMachine
    -0.05
    POSITIVE LOGITS
    Hey
    0.12
     Hey
    0.09
    breaker
    0.09
     hey
    0.08
    ready
    0.08
     hei
    0.07
     didn
    0.07
     grabbed
    0.07
     Speedway
    0.07
     fooled
    0.07
    Act Density 0.009%

    No Known Activations