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

    Neuronpedia

    INDEX
    Explanations

    languages learning and action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    នឹង
    0.41
     starost
    0.39
     pectoral
    0.38
     ადა
    0.38
    വൃ
    0.38
    blank
    0.37
     magnifier
    0.37
    檜
    0.36
     sucrose
    0.35
    analysis
    0.35
    POSITIVE LOGITS
    阀
    0.47
     learn
    0.41
    ilda
    0.39
    Compras
    0.39
    学び
    0.38
    apprentissage
    0.38
    Laura
    0.38
    Guidelines
    0.38
    学习
    0.37
    ступ
    0.36
    Act Density 0.000%

    No Known Activations