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

    Neuronpedia

    INDEX
    Explanations

    Object destruction/deallocation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atoi
    -0.07
    ov
    -0.07
     خورد
    -0.07
     tourists
    -0.07
    (scores
    -0.06
    _counts
    -0.06
     incest
    -0.06
     stripes
    -0.06
    itou
    -0.06
    “Yes
    -0.06
    POSITIVE LOGITS
    عية
    0.06
    ILITY
    0.06
    حه
    0.06
    ($_
    0.06
     Inventory
    0.06
    <Func
    0.06
    ْع
    0.06
    ジア
    0.06
    rait
    0.06
    če
    0.06
    Act Density 0.030%

    No Known Activations