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

    Neuronpedia

    INDEX
    Explanations

    /*

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (especially floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Мик
    -0.06
     stitching
    -0.06
     geschichten
    -0.06
    ��
    -0.06
     earthquake
    -0.06
    	Dictionary
    -0.06
     leakage
    -0.06
     relevant
    -0.06
     electrodes
    -0.06
     refusal
    -0.06
    POSITIVE LOGITS
     Compute
    0.07
    -trans
    0.06
    axios
    0.06
    .rotate
    0.06
     webcam
    0.06
     gere
    0.06
    $conn
    0.06
     populous
    0.06
    ำ
    0.06
    aoke
    0.06
    Act Density 0.000%

    No Known Activations