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

    Neuronpedia

    INDEX
    Explanations

    Scientific article titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _checksum
    -0.07
    porte
    -0.07
    🔊
    -0.07
    Muon
    -0.07
    ⚜
    -0.07
     ensuite
    -0.07
    assuming
    -0.07
    的比例
    -0.07
    /sp
    -0.06
    _bins
    -0.06
    POSITIVE LOGITS
     Gü
    0.07
     presentation
    0.07
    困扰
    0.07
     כת
    0.07
     produk
    0.06
     endereco
    0.06
    ,body
    0.06
    orrh
    0.06
     kh
    0.06
    _RA
    0.06
    Act Density 0.061%

    No Known Activations