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

    Neuronpedia

    INDEX
    Explanations

    ('

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     talents
    -0.08
     articulate
    -0.08
    itone
    -0.07
    自治
    -0.07
     forgiveness
    -0.07
    utils
    -0.07
     workspace
    -0.07
    四个方面
    -0.07
     resurrection
    -0.07
     details
    -0.07
    POSITIVE LOGITS
    ("
    0.08
    ('
    0.08
    てしま
    0.07
    ("__
    0.07
     glColor
    0.07
    襚
    0.07
    _COMMAND
    0.06
    燮
    0.06
    꼍
    0.06
    섬
    0.06
    Act Density 0.073%

    No Known Activations