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

    Neuronpedia

    INDEX
    Explanations

    categorizing or specifying things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ठी
    0.38
    ړه
    0.34
    وریت
    0.33
    (',',
    0.33
    utilized
    0.33
    makeConstraints
    0.32
    ঠিক
    0.32
     принимает
    0.32
     veuillez
    0.32
    Notwithstanding
    0.32
    POSITIVE LOGITS
     installing
    1.35
     accessing
    1.33
     getting
    1.31
     owning
    1.27
     obtaining
    1.27
     selecting
    1.27
     storing
    1.25
     putting
    1.23
     having
    1.23
     removing
    1.23
    Act Density 0.519%

    No Known Activations