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

    Neuronpedia

    INDEX
    Explanations

    user requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    勸
    0.40
     scrutinized
    0.39
    䏍
    0.39
     constat
    0.38
     способность
    0.38
     sacrifices
    0.38
     poblaciones
    0.37
    notlocked
    0.37
     carbonic
    0.37
    _{\{
    0.37
    POSITIVE LOGITS
     request
    1.16
     requests
    1.06
    请求
    1.00
     Request
    0.99
    Request
    0.98
    request
    0.96
    Requests
    0.96
     requested
    0.96
     requesting
    0.94
     요청
    0.93
    Act Density 0.742%

    No Known Activations