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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tabs
    -0.07
     आत
    -0.07
    βι
    -0.07
    玻璃
    -0.06
    ительное
    -0.06
     lớp
    -0.06
    치를
    -0.06
    ilere
    -0.06
     STILL
    -0.06
    итель
    -0.06
    POSITIVE LOGITS
    For
    0.11
     For
    0.08
     Carla
    0.07
    "For
    0.07
    (for
    0.06
    for
    0.06
     Damian
    0.06
    “For
    0.06
     Vladimir
    0.06
    <Data
    0.06
    Act Density 0.037%

    No Known Activations