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

    Neuronpedia

    INDEX
    Explanations

    behind their backs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     угле
    0.38
     geldiniz
    0.35
     конден
    0.35
     بلد
    0.35
     alé
    0.34
     subjectivity
    0.34
     আক্রান্ত
    0.34
    年来
    0.33
    obus
    0.33
     resetCounters
    0.33
    POSITIVE LOGITS
     behind
    2.64
    behind
    2.52
    Behind
    2.44
     Behind
    2.41
     detrás
    1.98
     dietro
    1.85
     derrière
    1.84
    背后
    1.81
     backstage
    1.78
     پشت
    1.74
    Act Density 0.128%

    No Known Activations