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

    Neuronpedia

    INDEX
    Explanations

    Blocking, anchors, routing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    籽
    0.43
     Kathleen
    0.42
    する方法
    0.39
     expression
    0.37
    ಳಗ
    0.37
    রাই
    0.37
    Saxon
    0.37
     evaporated
    0.36
    সেল
    0.36
     librarians
    0.36
    POSITIVE LOGITS
     блоки
    0.52
     मॉल
    0.44
     mall
    0.42
     блока
    0.41
    cheng
    0.41
     Enabled
    0.41
     Blocking
    0.40
     sensi
    0.40
     блок
    0.39
     bloqueo
    0.39
    Act Density 0.001%

    No Known Activations