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

    Neuronpedia

    INDEX
    Explanations

    introducing contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    1.21
    ्मण
    1.00
    eenth
    0.98
    চ
    0.97
    گزاری
    0.95
    gripper
    0.94
    ంత
    0.92
    er
    0.92
    ことになる
    0.92
    𝐝
    0.92
    POSITIVE LOGITS
    ched
    0.82
    Lack
    0.77
     setTitle
    0.76
    <0xA2>
    0.74
    Prosecutors
    0.74
    Appear
    0.73
    rons
    0.73
    ร์
    0.73
    RFID
    0.73
    rw
    0.73
    Act Density 0.201%

    No Known Activations