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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric literals (floating‐point numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ماسه
    -0.07
    ицин
    -0.06
     Hir
    -0.06
    pond
    -0.06
    착
    -0.06
    _COMPLETE
    -0.06
    ینک
    -0.06
    .ly
    -0.06
     Anyway
    -0.06
    projects
    -0.06
    POSITIVE LOGITS
     Leg
    0.07
     Form
    0.07
     mga
    0.06
     CP
    0.06
     empowered
    0.06
    <|start_header_id|>
    0.06
     Georg
    0.06
     leg
    0.06
    VES
    0.06
    },↵↵
    0.06
    Act Density 0.011%

    No Known Activations