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

    Neuronpedia

    INDEX
    Explanations

    let

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    、“
    0.40
    istic
    0.39
    ，“
    0.39
    toolStripButton
    0.39
    “”
    0.39
    ณี
    0.38
     “…
    0.38
    queros
    0.38
    izaciones
    0.36
    ّم
    0.36
    POSITIVE LOGITS
     us
    0.47
    ഴിലാ
    0.43
    讓你
    0.42
     нас
    0.41
    derr
    0.40
     生命
    0.40
    让你
    0.40
     estejam
    0.39
    让我们
    0.39
     nás
    0.38
    Act Density 0.076%

    No Known Activations