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

    Neuronpedia

    INDEX
    Explanations

    Disbelief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     明
    -0.06
    法
    -0.06
    _lead
    -0.06
     Magnetic
    -0.06
    reib
    -0.06
     福
    -0.06
    léd
    -0.06
     Brig
    -0.06
    لی
    -0.06
    647
    -0.06
    POSITIVE LOGITS
     versa
    0.07
    (fabs
    0.06
    ibir
    0.06
     especial
    0.06
    Dispose
    0.06
    loomberg
    0.06
    ]
↵
    0.06
    sylvania
    0.06
    ＆
    0.06
     prohibits
    0.06
    Act Density 0.040%

    No Known Activations