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

    Neuronpedia

    INDEX
    Explanations

    word followed by to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kepada
    1.19
     unto
    0.87
    ไปยัง
    0.86
    ToObject
    0.86
    ToServer
    0.85
     към
    0.81
    ដល់
    0.81
    ให้กับ
    0.78
     إلى
    0.75
    ToFile
    0.74
    POSITIVE LOGITS
    ጲ
    0.40
    ಮು
    0.37
    €
    0.35
     تاع
    0.35
    ଅ
    0.34
    리기
    0.33
    argout
    0.33
    漓
    0.32
    Computing
    0.31
     কারখানা
    0.31
    Act Density 0.064%

    No Known Activations