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

    Neuronpedia

    INDEX
    Explanations

    SVG code

    np_max-act · gemini-2.0-flash

    The neuron never activates on any tokens—it effectively doesn’t detect anything.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    //---------------------------------------------------------------------------↵
    -0.07
    ỏ
    -0.07
    arp
    -0.06
    机场
    -0.06
    zero
    -0.06
    maker
    -0.06
     provoz
    -0.06
    िकत
    -0.06
     willingness
    -0.06
     color
    -0.06
    POSITIVE LOGITS
    _regions
    0.07
    _PATCH
    0.07
     Writers
    0.07
    .lon
    0.06
     Claud
    0.06
     bytearray
    0.06
     qty
    0.06
     Truy
    0.06
     sdk
    0.06
     appell
    0.06
    Act Density 0.001%

    No Known Activations