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

    Neuronpedia

    INDEX
    Explanations

    Facebook Houston operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ములు
    0.81
    Commande
    0.78
     करण्यात
    0.77
    memb
    0.77
     diminue
    0.76
     দাদা
    0.76
    ဤ
    0.76
     batalha
    0.75
    vae
    0.75
    পত্র
    0.74
    POSITIVE LOGITS
     legal
    0.68
     counted
    0.67
    ١
    0.66
    菜
    0.65
     kissed
    0.64
     grave
    0.63
    ht
    0.63
     or
    0.63
    テッド
    0.63
     poly
    0.63
    Act Density 0.000%

    No Known Activations