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

    Neuronpedia

    INDEX
    Explanations

    slice

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the “slice” method (i.e. the token “slice” in code).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Th
    -0.07
    уля
    -0.06
    AN
    -0.06
    ann
    -0.06
     安
    -0.06
    ComboBox
    -0.06
    iang
    -0.06
    Kom
    -0.06
     Kom
    -0.06
     Simon
    -0.06
    POSITIVE LOGITS
    wow
    0.07
    .splice
    0.07
     mutableListOf
    0.07
    .pe
    0.07
    spender
    0.07
     cerebral
    0.06
    _profit
    0.06
     unconstitutional
    0.06
    険
    0.06
     uplifting
    0.06
    Act Density 0.004%

    No Known Activations