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

    Neuronpedia

    INDEX
    Explanations

    care about, care for, matters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     я
    1.30
     일
    1.27
     п
    1.18
     Tasma
    1.16
     но
    1.09
     м
    1.06
    не
    1.06
     ט
    1.06
     пи
    1.05
     저는
    1.03
    POSITIVE LOGITS
    ur
    1.41
    ot
    1.24
    ts
    1.20
    ad
    1.17
    oks
    1.17
    ীয়
    1.09
    ast
    1.07
    ाइन
    1.07
    blur
    1.06
    ո
    1.06
    Act Density 0.183%

    No Known Activations