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

    Neuronpedia

    INDEX
    Explanations

    forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ܙ
    0.44
    啉
    0.42
    铮
    0.41
    भाषित
    0.40
     اختی
    0.39
     ADMINISTR
    0.39
     администра
    0.38
    দ্দীন
    0.38
    嗥
    0.38
    찹
    0.38
    POSITIVE LOGITS
     forces
    1.69
     force
    1.66
     fuerzas
    1.41
    forces
    1.39
     Forces
    1.38
     fuerza
    1.38
     forças
    1.34
    Forces
    1.34
    force
    1.33
     força
    1.29
    Act Density 0.063%

    No Known Activations