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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _axis
    -0.07
     EXPRESS
    -0.06
    โย
    -0.06
    Це
    -0.06
     противоп
    -0.06
     bloody
    -0.06
    國
    -0.06
     planta
    -0.06
     comp
    -0.06
     southern
    -0.06
    POSITIVE LOGITS
     please
    0.07
    _street
    0.06
     củ
    0.06
    ographies
    0.06
    _pins
    0.06
    hashed
    0.06
    trie
    0.06
     recycle
    0.06
    erculosis
    0.06
    -if
    0.06
    Act Density 0.142%

    No Known Activations