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

    Neuronpedia

    INDEX
    Explanations

    foreign objects or bodies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.61
    िट
    1.52
     posteriori
    1.51
     varient
    1.42
    дцать
    1.41
    ется
    1.38
     बजे
    1.37
     dimmer
    1.36
     ответствен
    1.34
    َى
    1.33
    POSITIVE LOGITS
    йки
    2.09
    y
    1.80
    ası
    1.70
    arxiv
    1.69
    p
    1.69
    e
    1.65
    randint
    1.60
    ni
    1.59
     NGOs
    1.57
    滉
    1.56
    Act Density 0.000%

    No Known Activations