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

    Neuronpedia

    INDEX
    Explanations

    requests for information

    np_max-act · gemini-2.0-flash

    This neuron activates on the German instruction term “Eingabe” (and its subparts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     orth
    -0.06
    Ne
    -0.06
    Requirements
    -0.06
    _pre
    -0.06
     Ne
    -0.06
    	slot
    -0.06
    )this
    -0.06
    (r
    -0.06
     pg
    -0.06
     BD
    -0.06
    POSITIVE LOGITS
    ظيف
    0.06
     мяг
    0.06
     خاک
    0.06
     хоч
    0.06
     Aspen
    0.06
     количество
    0.06
     ден
    0.06
     trembling
    0.06
    ,buf
    0.06
    ße
    0.06
    Act Density 0.067%

    No Known Activations