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

    Neuronpedia

    INDEX
    Explanations

    Inferences and conclusions

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases related to reasoning, inference, and uncertainty (e.g. "determine," "possible," "infer," etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sitting
    -0.07
     تشخیص
    -0.07
     awe
    -0.07
     Vegetable
    -0.07
    adu
    -0.07
    .wav
    -0.06
     Keller
    -0.06
    attle
    -0.06
    .orders
    -0.06
    ็ตาม
    -0.06
    POSITIVE LOGITS
     �
    0.07
     clk
    0.07
     animate
    0.06
     فضای
    0.06
     vertices
    0.06
    tabla
    0.06
     ax
    0.06
    _render
    0.06
    _strlen
    0.06
     prostitution
    0.06
    Act Density 0.046%

    No Known Activations