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

    Neuronpedia

    INDEX
    Explanations

    route

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is find mentions of routing or path‐planning (e.g., “route,” “routing,” “pathfinding,” “optimize route”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (iterator
    -0.07
    ImageView
    -0.06
     whatsapp
    -0.06
    spotify
    -0.06
    .addChild
    -0.06
    ивать
    -0.06
    (It
    -0.06
    Recv
    -0.06
     характер
    -0.06
    React
    -0.06
    POSITIVE LOGITS
     techn
    0.07
     PERF
    0.07
     fern
    0.07
    ::~
    0.06
    ˆ
    0.06
    nish
    0.06
     MIC
    0.06
    _mB
    0.06
     Design
    0.06
    (after
    0.06
    Act Density 0.019%

    No Known Activations