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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on numeric tokens (version numbers, floats, dimensions, offsets, etc.) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    earchBar
    -0.07
    _REPEAT
    -0.07
     ();↵↵
    -0.07
    ._↵↵
    -0.06
     ());↵↵
    -0.06
    olang
    -0.06
     Rim
    -0.06
    +d
    -0.06
     charities
    -0.06
     πολ
    -0.06
    POSITIVE LOGITS
    ">
↵
    0.09
     curator
    0.07
     กระ
    0.07
     tro
    0.07
     gaz
    0.07
     cam
    0.06
     обл
    0.06
    ekten
    0.06
     female
    0.06
    }/>
    0.06
    Act Density 0.002%

    No Known Activations