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

    Neuronpedia

    INDEX
    Explanations

    hello

    np_max-act · gemini-2.0-flash

    This neuron activates on the English greeting “Hello.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     infrastructure
    -0.07
    actor
    -0.07
    yahoo
    -0.06
    esper
    -0.06
     пти
    -0.06
    ROKE
    -0.06
    -An
    -0.06
    vf
    -0.06
     champions
    -0.06
     engulf
    -0.06
    POSITIVE LOGITS
    .");↵
    0.07
    Pose
    0.07
     vodka
    0.06
    scene
    0.06
     Mature
    0.06
    Screens
    0.06
     COOKIE
    0.06
     namespaces
    0.06
    體
    0.06
     Xen
    0.06
    Act Density 0.015%

    No Known Activations