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

    Neuronpedia

    INDEX
    Explanations

    your questions or requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IP
    0.55
    y
    0.55
    D
    0.52
    S
    0.51
    g
    0.50
    Z
    0.49
    prof
    0.48
    しょう
    0.47
    H
    0.47
    monitor
    0.46
    POSITIVE LOGITS
     важли
    0.45
     entsprechenden
    0.44
     вигляді
    0.44
     любви
    0.42
     점점
    0.42
     нашу
    0.42
     способом
    0.42
     {}>
    0.41
     חיצוני
    0.41
     તમારી
    0.41
    Act Density 0.027%

    No Known Activations