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

    Neuronpedia

    INDEX
    Explanations

    Loveisrespect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equivalent
    0.85
     directly
    0.74
     specific
    0.72
     beyond
    0.71
     ensure
    0.70
     dynamic
    0.70
     related
    0.69
     path
    0.68
     check
    0.68
     pull
    0.68
    POSITIVE LOGITS
     Çocuk
    1.24
     Wrong
    1.15
     Them
    1.15
     Tomorrow
    1.13
     Gonna
    1.10
     Меня
    1.10
     Yourself
    1.09
     Música
    1.07
     Không
    1.06
     Myself
    1.05
    Act Density 0.233%

    No Known Activations