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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    튿
    0.41
    }))$
    0.40
    ▫
    0.40
    ahiya
    0.38
     punches
    0.38
    জ্জামান
    0.37
     included
    0.37
     uomo
    0.36
    indazole
    0.36
     عند
    0.36
    POSITIVE LOGITS
     работы
    0.49
     THEM
    0.46
    came
    0.44
     WORK
    0.44
     práce
    0.43
    จิต
    0.43
    nois
    0.43
    TION
    0.43
     इसे
    0.42
     TASK
    0.42
    Act Density 0.003%

    No Known Activations