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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resentment
    -0.08
    hift
    -0.07
    쑹
    -0.07
    cling
    -0.07
     hectic
    -0.07
    微信群
    -0.07
    深渊
    -0.07
     speeds
    -0.07
    ☨
    -0.07
    _ms
    -0.07
    POSITIVE LOGITS
    	Y
    0.08
    镑
    0.07
    erg
    0.07
     pairwise
    0.07
     cos
    0.06
    RU
    0.06
     öner
    0.06
     BUS
    0.06
    在未来
    0.06
    臟
    0.06
    Act Density 0.020%

    No Known Activations