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

    Neuronpedia

    INDEX
    Explanations

    solve

    np_max-act · gemini-2.0-flash

    The neuron fires on the floating-point numeric values that follow the “solve” step in the experimental refinement details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _LOCATION
    -0.08
    ーン
    -0.07
     Mob
    -0.07
    moon
    -0.07
    pace
    -0.07
     mName
    -0.07
    /main
    -0.07
    !!}
    -0.07
    Leon
    -0.06
    AA
    -0.06
    POSITIVE LOGITS
    .Notify
    0.07
     문제
    0.07
     первый
    0.06
    [^
    0.06
    aussian
    0.06
     +
↵
    0.06
    {-#
    0.06
    .toHexString
    0.06
    �
    0.06
    (split
    0.06
    Act Density 0.000%

    No Known Activations