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

    Neuronpedia

    INDEX
    Explanations

    Unstructured data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruins
    -0.07
     RAW
    -0.06
     words
    -0.06
    ram
    -0.06
     variants
    -0.06
     soud
    -0.06
    Destination
    -0.06
     TBranch
    -0.06
     поход
    -0.06
    経
    -0.06
    POSITIVE LOGITS
    ecure
    0.07
     bestimm
    0.07
     Los
    0.07
    博士
    0.06
     coursework
    0.06
    _LANE
    0.06
     deciding
    0.06
    ид
    0.06
    ้ใน
    0.06
    athom
    0.06
    Act Density 0.000%

    No Known Activations