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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Center
    -0.06
    ordon
    -0.06
    picable
    -0.06
     Gä
    -0.06
    Destination
    -0.06
    otre
    -0.06
    Logic
    -0.06
    medium
    -0.05
    ์เซ
    -0.05
    ères
    -0.05
    POSITIVE LOGITS
    .ENTER
    0.07
    .ng
    0.07
    _pci
    0.07
    dbg
    0.07
    лось
    0.07
     Www
    0.06
    .getProduct
    0.06
    thumbs
    0.06
    مع
    0.06
     الخام
    0.06
    Act Density 0.164%

    No Known Activations