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

    Neuronpedia

    INDEX
    Explanations

    seeing

    np_max-act · gemini-2.0-flash

    This neuron responds to informal, conversational lead-in phrases that start with a gerund and refer back to a past encounter (e.g. “seeing them the other day…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     construed
    -0.06
     packets
    -0.06
     OK
    -0.06
     Vancouver
    -0.06
    Lemma
    -0.06
     erotique
    -0.06
     Alice
    -0.06
     sentences
    -0.06
    ames
    -0.06
     Capitol
    -0.06
    POSITIVE LOGITS
    िवर
    0.07
    ansi
    0.06
    σει
    0.06
    /google
    0.06
    ISR
    0.06
    _SW
    0.06
    RunLoop
    0.06
    Verify
    0.06
    стров
    0.06
     determinant
    0.06
    Act Density 0.098%

    No Known Activations