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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—integers, decimals, and related symbols (e.g. minus signs)—used in arithmetic expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .FindGameObjectWithTag
    -0.07
     };
↵
↵
    -0.07
     SqlConnection
    -0.07
     Cheese
    -0.07
    _From
    -0.06
    azar
    -0.06
    .localization
    -0.06
    ò
    -0.06
    ()↵↵
    -0.06
    ts
    -0.06
    POSITIVE LOGITS
    :*
    0.06
     Brisbane
    0.06
    现场
    0.06
     phil
    0.06
     arcs
    0.06
     somew
    0.06
    رض
    0.06
     dise
    0.06
     aft
    0.06
     ancestry
    0.06
    Act Density 0.006%

    No Known Activations