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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “code” or “coding,” i.e. it detects when the text is about learning or doing programming.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Texture
    -0.07
     newVal
    -0.07
     Tank
    -0.06
    anske
    -0.06
    _bulk
    -0.06
     bmp
    -0.06
    心理
    -0.06
     Ста
    -0.06
    慢
    -0.06
     ölüm
    -0.06
    POSITIVE LOGITS
     ingres
    0.07
     cheeses
    0.06
    _initial
    0.06
    serialize
    0.06
    cce
    0.06
     trata
    0.06
     fury
    0.06
     excludes
    0.06
     acc
    0.06
     uygulam
    0.06
    Act Density 0.029%

    No Known Activations