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

    Neuronpedia

    INDEX
    Explanations

    missing someone or something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     groe
    0.43
     imag
    0.43
     sauvegarde
    0.43
     defocus
    0.42
     trycatch
    0.42
     rediscover
    0.42
     aprendiz
    0.41
     optimizations
    0.41
     remem
    0.40
     redis
    0.40
    POSITIVE LOGITS
     having
    0.54
    Having
    0.53
     داشتن
    0.46
     tendo
    0.46
     Having
    0.45
     HAVING
    0.45
     rumbo
    0.43
    日常
    0.42
    having
    0.42
     ayant
    0.40
    Act Density 0.005%

    No Known Activations