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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    成绩
    -0.07
    idae
    -0.07
     accompanies
    -0.06
     территории
    -0.06
     Whe
    -0.06
    損
    -0.06
     Canon
    -0.06
     canon
    -0.06
     *.
    -0.06
    ока
    -0.06
    POSITIVE LOGITS
    .TypeOf
    0.08
     TInt
    0.06
    (IC
    0.06
    .TEXT
    0.06
    iffies
    0.06
     getter
    0.06
    _Get
    0.06
    ("/{
    0.06
    .isAuthenticated
    0.06
     т
    0.06
    Act Density 0.061%

    No Known Activations