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

    Neuronpedia

    INDEX
    Explanations

    old language word roots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     REGI
    0.55
    </b>
    0.52
     lagoons
    0.50
    лку
    0.49
     bude
    0.48
    ITUDE
    0.48
     Kec
    0.48
    ";
    0.47
    `;
    0.47
    LookAndFeels
    0.47
    POSITIVE LOGITS
    на
    0.61
    am
    0.60
    s
    0.59
     entendido
    0.58
    ad
    0.57
    ap
    0.56
    ak
    0.55
     લઇ
    0.55
    n
    0.55
    ک
    0.55
    Act Density 0.009%

    No Known Activations