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

    Neuronpedia

    INDEX
    Explanations

    roles and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     θ
    0.27
    ൃത്ത
    0.27
     \,
    0.25
     RCLCPP
    0.25
     పథ
    0.25
    ल्पनिक
    0.25
    ्मण
    0.24
     β
    0.24
     HashTable
    0.24
     \)
    0.24
    POSITIVE LOGITS
    '
    0.31
    ’
    0.29
    /
    0.25
    II
    0.24
    -
    0.23
    ALE
    0.22
    chwitz
    0.22
    US
    0.21
    Act
    0.21
    bla
    0.21
    Act Density 0.153%

    No Known Activations