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

    Neuronpedia

    INDEX
    Explanations

    long rectangles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ddots
    0.40
    ّ
    0.39
     દિ
    0.39
     ग्र
    0.37
     ни
    0.36
     اح
    0.36
    ]")]
    0.36
     طبي
    0.36
     compressive
    0.35
     заду
    0.35
    POSITIVE LOGITS
     وزارت
    0.40
    OGND
    0.40
    ัฒ
    0.40
     negroes
    0.40
    閪
    0.38
    GoString
    0.38
     एप्लीकेशन
    0.38
     traitor
    0.38
    ெற்ற
    0.38
    ივ
    0.38
    Act Density 0.000%

    No Known Activations