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

    Neuronpedia

    INDEX
    Explanations

    ail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swarm
    -0.07
     Stage
    -0.07
    卷
    -0.07
    von
    -0.07
    复仇
    -0.06
    .Include
    -0.06
     CONTACT
    -0.06
    ≴
    -0.06
    诘
    -0.06
     nâ
    -0.06
    POSITIVE LOGITS
     которое
    0.08
    ucz
    0.07
    为中国
    0.07
     trabajo
    0.07
     Cyprus
    0.07
     lj
    0.07
    Unmount
    0.07
    这件
    0.07
    (zip
    0.07
    _ART
    0.06
    Act Density 0.000%

    No Known Activations