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

    Neuronpedia

    INDEX
    Explanations

    sensitive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    兮
    -0.08
     EventType
    -0.07
    (dx
    -0.07
     Airbnb
    -0.07
    共青团
    -0.07
    薁
    -0.07
    来た
    -0.07
     lax
    -0.07
    ={(
    -0.07
     '=
    -0.07
    POSITIVE LOGITS
    пи
    0.08
     sensitive
    0.08
    同学
    0.07
     Вам
    0.07
    -sensitive
    0.07
    PAL
    0.07
     screen
    0.07
    IVING
    0.07
    _man
    0.07
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.06
    Act Density 0.012%

    No Known Activations