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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meget
    -0.07
    .OP
    -0.07
    徒步
    -0.07
     Homo
    -0.07
    ⊔
    -0.07
     metros
    -0.06
    حدود
    -0.06
    ⬟
    -0.06
    支部
    -0.06
    廉价
    -0.06
    POSITIVE LOGITS
     ],
    0.08
    ać
    0.07
    只要是
    0.07
    раб
    0.07
    Bring
    0.07
     spanish
    0.07
     UK
    0.06
    namespace
    0.06
     Vent
    0.06
     EntityManager
    0.06
    Act Density 0.001%

    No Known Activations