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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    стве
    -0.07
    샵
    -0.07
     Robots
    -0.06
    лы
    -0.06
     licences
    -0.06
    hecy
    -0.06
     лучше
    -0.06
     será
    -0.06
     Sampler
    -0.06
    化
    -0.06
    POSITIVE LOGITS
     apresent
    0.06
     conservation
    0.06
     INTERNAL
    0.06
     Depend
    0.06
     intelligent
    0.06
    _RESPONSE
    0.06
     Ma
    0.06
    Serializable
    0.05
     tq
    0.05
    SetBranch
    0.05
    Act Density 0.039%

    No Known Activations