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 floating‐point numeric values (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    антаж
    -0.07
     Charts
    -0.07
    мени
    -0.06
    ...'
    -0.06
    ่าย
    -0.06
    鮮
    -0.06
     bureauc
    -0.06
    ..."
    -0.06
    ад
    -0.06
    ví
    -0.06
    POSITIVE LOGITS
     -(
    0.07
    젤
    0.07
    idata
    0.07
     COMM
    0.07
     JAXB
    0.07
    	rb
    0.07
    <=$
    0.07
     divine
    0.06
    _IDLE
    0.06
     joueur
    0.06
    Act Density 0.043%

    No Known Activations