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

    Neuronpedia

    INDEX
    Explanations

    sm followed by common word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Duc
    0.77
     impossible
    0.71
    sed
    0.67
    ionate
    0.66
    mist
    0.66
    Mist
    0.66
     실수
    0.65
    Danny
    0.65
     mic
    0.64
     rostr
    0.64
    POSITIVE LOGITS
    Sm
    0.94
     sm
    0.93
    ART
    0.93
    earing
    0.92
     SM
    0.88
     Sm
    0.88
    arth
    0.86
    ARTER
    0.85
    oked
    0.85
    udging
    0.83
    Act Density 0.022%

    No Known Activations