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

    Neuronpedia

    INDEX
    Explanations

    tower height measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     działalności
    0.52
     działal
    0.51
     αριθ
    0.51
    ഴിലാ
    0.49
     פע
    0.48
     نظری
    0.48
     интерес
    0.47
     politische
    0.47
     интересно
    0.47
    ნიშვნ
    0.46
    POSITIVE LOGITS
    K
    0.53
    6
    0.52
    FL
    0.52
    8
    0.52
    W
    0.51
    7
    0.49
    ↵
    0.48
    X
    0.47
    L
    0.47
    en
    0.46
    Act Density 0.000%

    No Known Activations