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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    协议
    -0.07
    Shift
    -0.07
    将
    -0.07
    uples
    -0.07
     climates
    -0.07
    _intersection
    -0.07
     epilepsy
    -0.07
    425
    -0.06
    otate
    -0.06
     adjacent
    -0.06
    POSITIVE LOGITS
    orrh
    0.06
    pac
    0.06
              ↵
    0.06
     destruct
    0.06
     авг
    0.06
    .PostMapping
    0.06
    uos
    0.06
    BUTTONDOWN
    0.06
     Loft
    0.06
    ,test
    0.05
    Act Density 0.008%

    No Known Activations