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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the token “out,” as in phrases indicating something being removed or moved out.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     موارد
    -0.07
    ände
    -0.06
     integrating
    -0.06
    uste
    -0.06
     meiner
    -0.06
    _LOW
    -0.06
     over
    -0.06
    	memcpy
    -0.06
    uve
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     out
    0.10
     出
    0.09
     Out
    0.09
    出
    0.08
    нима
    0.07
     jar
    0.07
    .out
    0.07
    ΑΛ
    0.07
    iful
    0.07
     μά
    0.07
    Act Density 0.026%

    No Known Activations