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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cropped
    -0.07
    _->
    -0.07
     partic
    -0.06
     sửa
    -0.06
     Play
    -0.06
     XmlNode
    -0.06
     repertoire
    -0.06
    _resp
    -0.06
    _hor
    -0.06
    API
    -0.06
    POSITIVE LOGITS
     tah
    0.07
    rell
    0.07
     fallback
    0.07
    استان
    0.06
    back
    0.06
     😉↵↵
    0.06
     треба
    0.06
     insomnia
    0.06
     enclave
    0.06
     mund
    0.06
    Act Density 0.001%

    No Known Activations