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

    Neuronpedia

    INDEX
    Explanations

    building barriers against something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    includes
    0.43
    cleaned
    0.42
     includes
    0.41
    ಿಕೊಳ್ಳ
    0.39
    exclusive
    0.39
    omial
    0.39
    ósito
    0.39
    vehicle
    0.39
    ffle
    0.39
     involves
    0.38
    POSITIVE LOGITS
     Malcolm
    0.46
     Sebastian
    0.43
    ুতি
    0.41
    蕁
    0.41
     Sunderland
    0.38
     tileSize
    0.38
     Carl
    0.38
    നിയ
    0.37
     arrière
    0.37
     chống
    0.37
    Act Density 0.000%

    No Known Activations