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

    Neuronpedia

    INDEX
    Explanations

    Sunstone, Sunken, Shape of You

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.70
    AHN
    0.66
    AG
    0.65
    can
    0.58
    णसी
    0.58
    gana
    0.56
    går
    0.55
    پردا
    0.55
    urre
    0.54
    ARING
    0.54
    POSITIVE LOGITS
    </h3>
    0.82
    ;
    0.67
    </td>
    0.66
    !
    0.66
     расска
    0.63
    </strong>
    0.63
    </h4>
    0.62
    <strong>
    0.61
    </h1>
    0.59
    </th>
    0.56
    Act Density 0.000%

    No Known Activations