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

    Neuronpedia

    INDEX
    Explanations

    "Let's" followed by an action verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그렇
    0.47
     dacă
    0.46
     situación
    0.43
     územ
    0.42
     rằng
    0.42
    lensFlare
    0.42
    釀
    0.41
     studente
    0.41
    ถุนายน
    0.41
     цього
    0.41
    POSITIVE LOGITS
     us
    0.64
     me
    0.61
     together
    0.47
     an
    0.46
    pid
    0.46
     lets
    0.45
     herv
    0.44
     her
    0.44
    共に
    0.43
     nhau
    0.43
    Act Density 0.023%

    No Known Activations