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

    Neuronpedia

    INDEX
    Explanations

    guardian Chanel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sinful
    0.42
    तमंद
    0.40
    拁
    0.39
    ନ୍ତ
    0.39
     Vivekananda
    0.38
    ़
    0.38
    uniformly
    0.38
    länd
    0.38
    型の
    0.38
     kjø
    0.37
    POSITIVE LOGITS
    pid
    0.37
    和服务
    0.36
     Hao
    0.36
    groovy
    0.36
    guardian
    0.35
     Chanel
    0.35
     Loop
    0.35
    '$.
    0.35
     guardian
    0.35
     Channel
    0.34
    Act Density 0.000%

    No Known Activations