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

    Neuronpedia

    INDEX
    Explanations

    concepts and abstract ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lint
    0.46
    rx
    0.41
    chis
    0.41
     rado
    0.40
    lord
    0.39
    ler
    0.39
    ry
    0.38
    lines
    0.38
    loom
    0.38
    gun
    0.37
    POSITIVE LOGITS
     између
    0.56
     इकट्ठा
    0.46
     između
    0.45
     между
    0.45
     મોબાઇલ
    0.45
    ジネス
    0.44
     movilidad
    0.42
    之間的
    0.41
     Between
    0.40
    玥
    0.40
    Act Density 0.001%

    No Known Activations