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

    Neuronpedia

    INDEX
    Explanations

    electrical engineering and technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chase
    0.49
     Strip
    0.48
     Assistant
    0.46
     Ble
    0.44
     BLE
    0.44
     English
    0.43
     Car
    0.42
     a
    0.42
     an
    0.42
     Profit
    0.42
    POSITIVE LOGITS
    бах
    0.52
    т
    0.45
    ме
    0.44
    GONDOR
    0.44
    Negative
    0.43
    বর
    0.42
    ాం
    0.42
    0.42
    Bangladesh
    0.41
    не
    0.41
    Act Density 0.000%

    No Known Activations