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

    Neuronpedia

    INDEX
    Explanations

    add

    np_max-act · gemini-2.0-flash

    This neuron fires on Go source‐code identifiers—especially PascalCase names (e.g. types, constants, methods) used in Kubernetes API registration.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     perf
    -0.06
     serg
    -0.06
     pcs
    -0.06
    스로
    -0.06
    QB
    -0.06
     работе
    -0.06
     применения
    -0.06
    reward
    -0.06
    7
    -0.06
     эконом
    -0.06
    POSITIVE LOGITS
     зависимости
    0.08
    FLICT
    0.07
     Float
    0.07
     contentValues
    0.06
    ertos
    0.06
    vatel
    0.06
     Conc
    0.06
     понять
    0.06
     нес
    0.06
    Coeff
    0.06
    Act Density 0.008%

    No Known Activations