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

    Neuronpedia

    INDEX
    Explanations

    social organization and space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cæ
    0.37
     Każ
    0.37
     ainfi
    0.36
     (=
    0.36
    ء
    0.35
     (|
    0.35
    urp
    0.35
     прямо
    0.34
     méthode
    0.34
     있기
    0.34
    POSITIVE LOGITS
    patial
    0.39
    ના
    0.38
     রবি
    0.37
    াচ্ছে
    0.37
    壤
    0.37
     startup
    0.37
    狀況
    0.36
     j
    0.36
    複雜
    0.36
     robotics
    0.36
    Act Density 0.043%

    No Known Activations