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

    Neuronpedia

    INDEX
    Explanations

    Parts and separation

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of architectural structural elements (e.g., walls).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pipe
    -0.07
     Algorithm
    -0.07
     Parcel
    -0.06
    ucchini
    -0.06
     Heavenly
    -0.06
     HDC
    -0.06
     Remote
    -0.06
     bos
    -0.06
     Arcade
    -0.06
     Millet
    -0.06
    POSITIVE LOGITS
    (evt
    0.08
    _coll
    0.07
    .exc
    0.07
    ☴
    0.07
     uncont
    0.07
    _tracking
    0.06
     thé
    0.06
    /web
    0.06
    /react
    0.06
    .pe
    0.06
    Act Density 0.034%

    No Known Activations